Publications

2024

• Anticipatory music transformer. John Thickstun, D. Hall, Chris Donahue, Percy Liang. Transcations of Machine Learning Research (TMLR), 2024.

  @article{thickstun2024anticipatory,
    author = {John Thickstun and D. Hall and Chris Donahue and Percy Liang},
    journal = {Transcations of Machine Learning Research (TMLR)},
    title = {Anticipatory Music Transformer},
    volume = {0},
    year = {2024},
  }
  

  [bib] [paper]
  
• Robust distortion-free watermarks for language models. Rohith Kuditipudi, John Thickstun, Tatsunori Hashimoto, Percy Liang. Transcations of Machine Learning Research (TMLR), 2024.

  @article{kuditipudi2024robust,
    author = {Rohith Kuditipudi and John Thickstun and Tatsunori Hashimoto and Percy Liang},
    journal = {Transcations of Machine Learning Research (TMLR)},
    title = {Robust Distortion-free Watermarks for Language Models},
    volume = {0},
    year = {2024},
  }
  

  [bib] [paper]
  
• MLAgentBench: evaluating language agents on machine learning experimentation. Qian Huang, Jian Vora, Percy Liang, Jure Leskovec. International Conference on Machine Learning (ICML), 2024.

  @inproceedings{huang2024research,
    author = {Qian Huang and Jian Vora and Percy Liang and Jure Leskovec},
    booktitle = {International Conference on Machine Learning (ICML)},
    title = {{MLAgentBench}: Evaluating Language Agents on Machine Learning Experimentation},
    year = {2024},
  }
  

  [bib] [paper]
  
• Prismatic VLMs: investigating the design space of visually-conditioned language models. Siddharth Karamcheti, Suraj Nair, Ashwin Balakrishna, Percy Liang, Thomas Kollar, Dorsa Sadigh. International Conference on Machine Learning (ICML), 2024.

  @inproceedings{karamcheti2024prismatic,
    author = {Siddharth Karamcheti and Suraj Nair and Ashwin Balakrishna and Percy Liang and Thomas Kollar and Dorsa Sadigh},
    booktitle = {International Conference on Machine Learning (ICML)},
    title = {Prismatic {VLM}s: Investigating the Design Space of Visually-Conditioned Language Models},
    year = {2024},
  }
  

  [bib] [paper]
  
• On the societal impact of open foundation models. Sayash Kapoor, Rishi Bommasani, Kevin Klyman, Shayne Longpre, Ashwin Ramaswami, Peter Cihon, Aspen Hopkins, Kevin Bankston, Stella Biderman, Miranda Bogen, Rumman Chowdhury, Alex Engler, Peter Henderson, Yacine Jernite, Seth Lazar, Stefano Maffulli, Alondra Nelson, Joelle Pineau, Aviya Skowron, Dawn Song, Victor Storchan, Daniel Zhang, Daniel E. Ho, Percy Liang, Arvind Narayanan. International Conference on Machine Learning (Position Paper Track) (ICML), 2024.

  @inproceedings{kapoor2024open,
    author = {Sayash Kapoor and Rishi Bommasani and Kevin Klyman and Shayne Longpre and Ashwin Ramaswami and Peter Cihon and Aspen Hopkins and Kevin Bankston and Stella Biderman and Miranda Bogen and Rumman Chowdhury and Alex Engler and Peter Henderson and Yacine Jernite and Seth Lazar and Stefano Maffulli and Alondra Nelson and Joelle Pineau and Aviya Skowron and Dawn Song and Victor Storchan and Daniel Zhang and Daniel E. Ho and Percy Liang and Arvind Narayanan},
    booktitle = {International Conference on Machine Learning (Position Paper Track) (ICML)},
    title = {On the Societal Impact of Open Foundation Models},
    year = {2024},
  }
  

  [bib] [paper]
  
• A safe harbor for AI evaluation and red teaming. Shayne Longpre, Sayash Kapoor, Kevin Klyman, Ashwin Ramaswami, Rishi Bommasani, Borhane Blili-Hamelin, Yangsibo Huang, Aviya Skowron, Zheng-Xin Yong, Suhas Kotha, Yi Zeng, Weiyan Shi, Xianjun Yang, Reid Southen, Alexander Robey, Patrick Chao, Diyi Yang, Ruoxi Jia, Daniel Kang, Sandy Pentland, Arvind Narayanan, Percy Liang, Peter Henderson. International Conference on Machine Learning (Position Paper Track) (ICML), 2024.

  @inproceedings{longpre2024safe,
    author = {Shayne Longpre and Sayash Kapoor and Kevin Klyman and Ashwin Ramaswami and Rishi Bommasani and Borhane Blili-Hamelin and Yangsibo Huang and Aviya Skowron and Zheng-Xin Yong and Suhas Kotha and Yi Zeng and Weiyan Shi and Xianjun Yang and Reid Southen and Alexander Robey and Patrick Chao and Diyi Yang and Ruoxi Jia and Daniel Kang and Sandy Pentland and Arvind Narayanan and Percy Liang and Peter Henderson},
    booktitle = {International Conference on Machine Learning (Position Paper Track) (ICML)},
    title = {A Safe Harbor for {AI} Evaluation and Red Teaming},
    year = {2024},
  }
  

  [bib] [paper]
  
• Benchmarking and improving generator-validator consistency of language models. Xiang Lisa Li, Vaishnavi Shrivastava, Siyan Li, Tatsunori Hashimoto, Percy Liang. International Conference on Learning Representations (ICLR), 2024.

  @inproceedings{li2024consistency,
    author = {Xiang Lisa Li and Vaishnavi Shrivastava and Siyan Li and Tatsunori Hashimoto and Percy Liang},
    booktitle = {International Conference on Learning Representations (ICLR)},
    title = {Benchmarking and Improving Generator-Validator Consistency of Language Models},
    year = {2024},
  }
  

  [bib] [paper]
  
• Large language models as analogical reasoners. Michihiro Yasunaga, Xinyun Chen, Yujia Li, Panupong Pasupat, J. Leskovec, Percy Liang, Ed H. Chi, Denny Zhou. International Conference on Learning Representations (ICLR), 2024.

  @inproceedings{yasunaga2024analogical,
    author = {Michihiro Yasunaga and Xinyun Chen and Yujia Li and Panupong Pasupat and J. Leskovec and Percy Liang and Ed H. Chi and Denny Zhou},
    booktitle = {International Conference on Learning Representations (ICLR)},
    title = {Large Language Models as Analogical Reasoners},
    year = {2024},
  }
  

  [bib] [paper]
  
• On the learnability of watermarks for language models. Chenchen Gu, Xiang Lisa Li, Percy Liang, Tatsunori Hashimoto. International Conference on Learning Representations (ICLR), 2024.

  @inproceedings{gu2024watermarks,
    author = {Chenchen Gu and Xiang Lisa Li and Percy Liang and Tatsunori Hashimoto},
    booktitle = {International Conference on Learning Representations (ICLR)},
    title = {On the Learnability of Watermarks for Language Models},
    year = {2024},
  }
  

  [bib] [paper]
  
• MedAlign: a clinician-generated dataset for instruction following with electronic medical records. S. Fleming, A. Lozano, W. Haberkorn, Jenelle A. Jindal, E. Reis, Rahul Thapa, L. Blankemeier, Julian Z. Genkins, E. Steinberg, A. Nayak, Birju S. Patel, Chia-Chun Chiang, A. Callahan, Zepeng Huo, S. Gatidis, S. Adams, Oluseyi Fayanju, Shreya J. Shah, Thomas Savage, Ethan Goh, A. Chaudhari, N. Aghaeepour, Christopher D. Sharp, M. Pfeffer, Percy Liang, Jonathan H. Chen, K. Morse, E. Brunskill, Jason Alan Fries, N. Shah. Association for the Advancement of Artificial Intelligence (AAAI), 2024.

  @inproceedings{fleming2024medalign,
    author = {S. Fleming and A. Lozano and W. Haberkorn and Jenelle A. Jindal and E. Reis and Rahul Thapa and L. Blankemeier and Julian Z. Genkins and E. Steinberg and A. Nayak and Birju S. Patel and Chia-Chun Chiang and A. Callahan and Zepeng Huo and S. Gatidis and S. Adams and Oluseyi Fayanju and Shreya J. Shah and Thomas Savage and Ethan Goh and A. Chaudhari and N. Aghaeepour and Christopher D. Sharp and M. Pfeffer and Percy Liang and Jonathan H. Chen and K. Morse and E. Brunskill and Jason Alan Fries and N. Shah},
    booktitle = {Association for the Advancement of Artificial Intelligence (AAAI)},
    title = {MedAlign: A Clinician-Generated Dataset for Instruction Following with Electronic Medical Records},
    year = {2024},
  }
  

  [bib] [paper]
  

2023

• The foundation model transparency index. Rishi Bommasani, Kevin Klyman, Shayne Longpre, Sayash Kapoor, Nestor Maslej, Betty Xiong, Daniel Zhang, Percy Liang. arXiv, 2023.

  @article{bommasani2023fmti,
    author = {Rishi Bommasani and Kevin Klyman and Shayne Longpre and Sayash Kapoor and Nestor Maslej and Betty Xiong and Daniel Zhang and Percy Liang},
    journal = {arXiv},
    title = {The Foundation Model Transparency Index},
    year = {2023},
  }
  

  [bib] [paper]
  
• Llamas know what gpts don't show: surrogate models for confidence estimation. Vaishnavi Shrivastava, Percy Liang, Ananya Kumar. arXiv, 2023.

  @article{shrivastava2023llamas,
    author = {Vaishnavi Shrivastava and Percy Liang and Ananya Kumar},
    journal = {arXiv},
    title = {Llamas Know What GPTs Don't Show: Surrogate Models for Confidence Estimation},
    year = {2023},
  }
  

  [bib] [paper]
  
• Data selection for language models via importance resampling. Sang Michael Xie, Shibani Santurkar, Tengyu Ma, Percy Liang. Advances in Neural Information Processing Systems (NeurIPS), 2023.

  @inproceedings{xie2023data,
    author = {Sang Michael Xie and Shibani Santurkar and Tengyu Ma and Percy Liang},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    title = {Data Selection for Language Models via Importance Resampling},
    year = {2023},
  }
  

  [bib] [paper]
  
• DoReMi: optimizing data mixtures speeds up language model pretraining. Sang Michael Xie, Hieu Pham, Xuanyi Dong, Nan Du, Hanxiao Liu, Yifeng Lu, Percy Liang, Quoc V. Le, Tengyu Ma, A. Yu. Advances in Neural Information Processing Systems (NeurIPS), 2023.

  @inproceedings{xie2023doremi,
    author = {Sang Michael Xie and Hieu Pham and Xuanyi Dong and Nan Du and Hanxiao Liu and Yifeng Lu and Percy Liang and Quoc V. Le and Tengyu Ma and A. Yu},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    title = {DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining},
    year = {2023},
  }
  

  [bib] [paper]
  
• PRODIGY: enabling in-context learning over graphs. Qian Huang, Hongyu Ren, Peng Chen, Gregor Krvzmanc, D. Zeng, Percy Liang, J. Leskovec. Advances in Neural Information Processing Systems (NeurIPS), 2023.

  @inproceedings{huang2023prodigy,
    author = {Qian Huang and Hongyu Ren and Peng Chen and Gregor Krvzmanc and D. Zeng and Percy Liang and J. Leskovec},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    title = {{PRODIGY}: Enabling In-context Learning Over Graphs},
    year = {2023},
  }
  

  [bib] [paper]
  
• Lexinvariant language models. Qian Huang, E. Zelikman, Sarah Chen, Yuhuai Wu, G. Valiant, Percy Liang. Advances in Neural Information Processing Systems (NeurIPS), 2023.

  @inproceedings{huang2023lexinvariant,
    author = {Qian Huang and E. Zelikman and Sarah Chen and Yuhuai Wu and G. Valiant and Percy Liang},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    title = {Lexinvariant Language Models},
    year = {2023},
  }
  

  [bib] [paper]
  
• Ecosystem-level analysis of deployed machine learning reveals homogeneous outcomes. Connor Toups, Rishi Bommasani, Kathleen A. Creel, Sarah H. Bana, Dan Jurafsky, Percy Liang. Advances in Neural Information Processing Systems (NeurIPS), 2023.

  @inproceedings{toups2023ecosystem,
    author = {Connor Toups and Rishi Bommasani and Kathleen A. Creel and Sarah H. Bana and Dan Jurafsky and Percy Liang},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    title = {Ecosystem-level Analysis of Deployed Machine Learning Reveals Homogeneous Outcomes},
    year = {2023},
  }
  

  [bib] [paper]
  
• AlpacaFarm: a simulation framework for methods that learn from human feedback. Yann Dubois, Xuechen Li, Rohan Taori, Tianyi Zhang, Ishaan Gulrajani, Jimmy Ba, Carlos Guestrin, Percy Liang, Tatsunori B. Hashimoto. Advances in Neural Information Processing Systems (NeurIPS), 2023.

  @inproceedings{dubois2023alpacafarm,
    author = {Yann Dubois and Xuechen Li and Rohan Taori and Tianyi Zhang and Ishaan Gulrajani and Jimmy Ba and Carlos Guestrin and Percy Liang and Tatsunori B. Hashimoto},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    title = {{AlpacaFarm}: A Simulation Framework for Methods that Learn from Human Feedback},
    year = {2023},
  }
  

  [bib] [paper]
  
• Cheaply evaluating inference efficiency metrics for autoregressive transformer apis. Deepak Narayanan, Keshav Santhanam, Peter Henderson, Rishi Bommasani, Tony Lee, Percy Liang. Advances in Neural Information Processing Systems (NeurIPS), 2023.

  @inproceedings{narayanan2023cheaply,
    author = {Deepak Narayanan and Keshav Santhanam and Peter Henderson and Rishi Bommasani and Tony Lee and Percy Liang},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    title = {Cheaply Evaluating Inference Efficiency Metrics for Autoregressive Transformer APIs},
    year = {2023},
  }
  

  [bib] [paper]
  
• Holistic evaluation of text-to-image models. Tony Lee, Michihiro Yasunaga, Chenlin Meng, Yifan Mai, Joon Sung Park, Agrim Gupta, Yunzhi Zhang, Deepak Narayanan, Hannah Teufel, Marco Bellagente, Minguk Kang, Taesung Park, J. Leskovec, Jun-Yan Zhu, Fei-Fei Li, Jiajun Wu, Stefano Ermon, Percy Liang. Neural Information Processing Systems Track on Datasets and Benchmarks (NeurIPS Datasets and Benchmarks), 2023.

  @inproceedings{lee2023holistic,
    author = {Tony Lee and Michihiro Yasunaga and Chenlin Meng and Yifan Mai and Joon Sung Park and Agrim Gupta and Yunzhi Zhang and Deepak Narayanan and Hannah Teufel and Marco Bellagente and Minguk Kang and Taesung Park and J. Leskovec and Jun-Yan Zhu and Fei-Fei Li and Jiajun Wu and Stefano Ermon and Percy Liang},
    booktitle = {Neural Information Processing Systems Track on Datasets and Benchmarks (NeurIPS Datasets and Benchmarks)},
    title = {Holistic Evaluation of Text-To-Image Models},
    year = {2023},
  }
  

  [bib] [paper]
  
• Lost in the middle: how language models use long contexts. Nelson F. Liu, Kevin Lin, John Hewitt, Ashwin Paranjape, Michele Bevilacqua, Fabio Petroni, Percy Liang. Transactions of the Association for Computational Linguistics (TACL), 2023.

  @article{liu2023lost,
    author = {Nelson F. Liu and Kevin Lin and John Hewitt and Ashwin Paranjape and Michele Bevilacqua and Fabio Petroni and Percy Liang},
    journal = {Transactions of the Association for Computational Linguistics (TACL)},
    title = {Lost in the Middle: How Language Models Use Long Contexts},
    volume = {0},
    year = {2023},
  }
  

  [bib] [paper]
  
• Evaluating verifiability in generative search engines. Nelson F. Liu, Tianyi Zhang, Percy Liang. Findings of Empirical Methods in Natural Language Processing (Findings of EMNLP), 2023.

  @inproceedings{liu2023evaluating,
    author = {Nelson F. Liu and Tianyi Zhang and Percy Liang},
    booktitle = {Findings of Empirical Methods in Natural Language Processing (Findings of EMNLP)},
    title = {Evaluating Verifiability in Generative Search Engines},
    year = {2023},
  }
  

  [bib] [paper]
  
• Evaluating human-language model interaction. Mina Lee, Megha Srivastava, Amelia Hardy, John Thickstun, Esin Durmus, Ashwin Paranjape, Ines Gerard-Ursin, Xiang Lisa Li, Faisal Ladhak, Frieda Rong, Rose E. Wang, Minae Kwon, Joon Sung Park, Hancheng Cao, Tony Lee, Rishi Bommasani, Michael Bernstein, Percy Liang. Transcations of Machine Learning Research (TMLR), 2023.

  @article{lee2023evaluating,
    author = {Mina Lee and Megha Srivastava and Amelia Hardy and John Thickstun and Esin Durmus and Ashwin Paranjape and Ines Gerard-Ursin and Xiang Lisa Li and Faisal Ladhak and Frieda Rong and Rose E. Wang and Minae Kwon and Joon Sung Park and Hancheng Cao and Tony Lee and Rishi Bommasani and Michael Bernstein and Percy Liang},
    journal = {Transcations of Machine Learning Research (TMLR)},
    title = {Evaluating Human-Language Model Interaction},
    volume = {0},
    year = {2023},
  }
  

  [bib] [paper]
  
• Trustworthy social bias measurement. Rishi Bommasani, Percy Liang. arXiv, 2023.

  @article{bommasani2023trustworthy,
    author = {Rishi Bommasani and Percy Liang},
    journal = {arXiv},
    title = {Trustworthy Social Bias Measurement},
    year = {2023},
  }
  

  [bib] [paper]
  
• Benchmarking large language models for news summarization. Tianyi Zhang, Faisal Ladhak, Esin Durmus, Percy Liang, K. McKeown, Tatsunori Hashimoto. arXiv, 2023.

  @article{zhang2023benchmarking,
    author = {Tianyi Zhang and Faisal Ladhak and Esin Durmus and Percy Liang and K. McKeown and Tatsunori Hashimoto},
    journal = {arXiv},
    title = {Benchmarking Large Language Models for News Summarization},
    year = {2023},
  }
  

  [bib] [paper]
  
• Demonstrate-Search-Predict: composing retrieval and language models for knowledge-intensive NLP. Omar Khattab, Keshav Santhanam, Xiang Lisa Li, David Hall, Percy Liang, Christopher Potts, Matei Zaharia. arXiv, 2023.

  @article{khattab2023dsp,
    author = {Omar Khattab and Keshav Santhanam and Xiang Lisa Li and David Hall and Percy Liang and Christopher Potts and Matei Zaharia},
    journal = {arXiv},
    title = {{Demonstrate-Search-Predict}: Composing retrieval and language models for knowledge-intensive {NLP}},
    year = {2023},
  }
  

  [bib] [paper]
  
• Generative agents: interactive simulacra of human behavior. Joon Sung Park, Joseph C. O'Brien, Carrie J. Cai, Meredith Ringel Morris, Percy Liang, Michael S. Bernstein. User Interface Software and Technology (UIST), 2023. Best paper award.

  @inproceedings{park2023generative,
    author = {Joon Sung Park and Joseph C. O'Brien and Carrie J. Cai and Meredith Ringel Morris and Percy Liang and Michael S. Bernstein},
    booktitle = {User Interface Software and Technology (UIST)},
    title = {Generative Agents: Interactive Simulacra of Human Behavior},
    year = {2023},
  }
  

  [bib] [paper]
  
• Foundation models and fair use. Peter Henderson, Xuechen Li, Dan Jurafsky, Tatsunori Hashimoto, Mark A. Lemley, Percy Liang. Journal of Machine Learning Research (JMLR), 2023.

  @article{henderson2023fairuse,
    author = {Peter Henderson and Xuechen Li and Dan Jurafsky and Tatsunori Hashimoto and Mark A. Lemley and Percy Liang},
    journal = {Journal of Machine Learning Research (JMLR)},
    title = {Foundation Models and Fair Use},
    volume = {0},
    year = {2023},
  }
  

  [bib] [paper]
  
• Ecosystem graphs: the social footprint of foundation models. Rishi Bommasani, Dilara Soylu, Thomas Liao, Kathleen A. Creel, Percy Liang. arXiv, 2023.

  @article{bommasani2023ecosystem,
    author = {Rishi Bommasani and Dilara Soylu and Thomas Liao and Kathleen A. Creel and Percy Liang},
    journal = {arXiv},
    title = {Ecosystem Graphs: The Social Footprint of Foundation Models},
    year = {2023},
  }
  

  [bib] [paper]
  
• Language-driven representation learning for robotics. Siddharth Karamcheti, Suraj Nair, Annie S. Chen, T. Kollar, Chelsea Finn, Dorsa Sadigh, Percy Liang. Robotics: Science and Systems (RSS), 2023. Best paper award finalist.

  @inproceedings{karamcheti2023voltron,
    author = {Siddharth Karamcheti and Suraj Nair and Annie S. Chen and T. Kollar and Chelsea Finn and Dorsa Sadigh and Percy Liang},
    booktitle = {Robotics: Science and Systems (RSS)},
    title = {Language-driven Representation Learning for Robotics},
    year = {2023},
  }
  

  [bib] [paper]
  
• High-throughput generative inference of large language models with a single GPU. Ying Sheng, Lianmin Zheng, Binhang Yuan, Zhuohan Li, Max Ryabinin, Daniel Y. Fu, Zhiqiang Xie, Beidi Chen, Clark W. Barrett, Joseph Gonzalez, Percy Liang, Christopher Ré, I. Stoica, Ce Zhang. International Conference on Machine Learning (ICML), 2023.

  @inproceedings{sheng2023flexgen,
    author = {Ying Sheng and Lianmin Zheng and Binhang Yuan and Zhuohan Li and Max Ryabinin and Daniel Y. Fu and Zhiqiang Xie and Beidi Chen and Clark W. Barrett and Joseph Gonzalez and Percy Liang and Christopher Ré and I. Stoica and Ce Zhang},
    booktitle = {International Conference on Machine Learning (ICML)},
    title = {High-throughput Generative Inference of Large Language Models with a Single {GPU}},
    year = {2023},
  }
  

  [bib] [paper]
  
• Retrieval-Augmented multimodal language modeling. Michihiro Yasunaga, Armen Aghajanyan, Weijia Shi, Rich James, Jure Leskovec, Percy Liang, Mike Lewis, Luke Zettlemoyer, Wen-tau Yih. International Conference on Machine Learning (ICML), 2023.

  @inproceedings{yasunaga2023retrieval,
    author = {Michihiro Yasunaga and Armen Aghajanyan and Weijia Shi and Rich James and Jure Leskovec and Percy Liang and Mike Lewis and Luke Zettlemoyer and Wen-tau Yih},
    booktitle = {International Conference on Machine Learning (ICML)},
    title = {Retrieval-Augmented Multimodal Language Modeling},
    year = {2023},
  }
  

  [bib] [paper]
  
• Whose opinions do language models reflect? Shibani Santurkar, Esin Durmus, Faisal Ladhak, Cinoo Lee, Percy Liang, Tatsunori Hashimoto. International Conference on Machine Learning (ICML), 2023.

  @inproceedings{santurkar2023opinions,
    author = {Shibani Santurkar and Esin Durmus and Faisal Ladhak and Cinoo Lee and Percy Liang and Tatsunori Hashimoto},
    booktitle = {International Conference on Machine Learning (ICML)},
    title = {Whose Opinions Do Language Models Reflect?},
    year = {2023},
  }
  

  [bib] [paper]
  
• Evaluating self-supervised learning via risk decomposition. Yann Dubois, Tatsunori Hashimoto, Percy Liang. International Conference on Machine Learning (ICML), 2023.

  @inproceedings{dubois2023evaluating,
    author = {Yann Dubois and Tatsunori Hashimoto and Percy Liang},
    booktitle = {International Conference on Machine Learning (ICML)},
    title = {Evaluating Self-Supervised Learning via Risk Decomposition},
    year = {2023},
  }
  

  [bib] [paper]
  
• Out-of-Domain robustness via targeted augmentations. Irena Gao, Shiori Sagawa, Pang Wei Koh, Tatsunori Hashimoto, Percy Liang. International Conference on Machine Learning (ICML), 2023.

  @inproceedings{gao2023targeted,
    author = {Irena Gao and Shiori Sagawa and Pang Wei Koh and Tatsunori Hashimoto and Percy Liang},
    booktitle = {International Conference on Machine Learning (ICML)},
    title = {Out-of-Domain Robustness via Targeted Augmentations},
    year = {2023},
  }
  

  [bib] [paper]
  
• Are sample-efficient NLP models more robust? Nelson F. Liu, Ananya Kumar, Percy Liang, Robin Jia. Association for Computational Linguistics (ACL), 2023.

  @inproceedings{liu2023sample,
    author = {Nelson F. Liu and Ananya Kumar and Percy Liang and Robin Jia},
    booktitle = {Association for Computational Linguistics (ACL)},
    title = {Are Sample-Efficient {NLP} Models More Robust?},
    year = {2023},
  }
  

  [bib] [paper]
  
• Do question answering modeling improvements hold across benchmarks? Nelson F. Liu, Tony Lee, Robin Jia, Percy Liang. Association for Computational Linguistics (ACL), 2023.

  @inproceedings{liu2023concurrence,
    author = {Nelson F. Liu and Tony Lee and Robin Jia and Percy Liang},
    booktitle = {Association for Computational Linguistics (ACL)},
    title = {Do Question Answering Modeling Improvements Hold Across Benchmarks?},
    year = {2023},
  }
  

  [bib] [paper]
  
• Beyond positive scaling: how negation impacts scaling trends of language models. Yuhui Zhang*, Michihiro Yasunaga*, Zhengping Zhou*, Jeff Z. HaoChen*, James Zou, Percy Liang, Serena Yeung. Findings of the Association for Computational Linguistics (Findings of ACL), 2023.

  @inproceedings{zhang2023beyond,
    author = {Yuhui Zhang and Michihiro Yasunaga and Zhengping Zhou and Jeff Z. HaoChen and James Zou and Percy Liang and Serena Yeung},
    booktitle = {Findings of the Association for Computational Linguistics (Findings of ACL)},
    title = {Beyond Positive Scaling: How Negation Impacts Scaling Trends of Language Models},
    year = {2023},
  }
  

  [bib] [paper]
  
• Contrastive decoding: open-ended text generation as optimization. Xiang Lisa Li, Ari Holtzman, Daniel Fried, Percy Liang, Jason Eisner, Tatsunori Hashimoto, Luke Zettlemoyer, M. Lewis. Association for Computational Linguistics (ACL), 2023.

  @inproceedings{li2023contrastive,
    author = {Xiang Lisa Li and Ari Holtzman and Daniel Fried and Percy Liang and Jason Eisner and Tatsunori Hashimoto and Luke Zettlemoyer and M. Lewis},
    booktitle = {Association for Computational Linguistics (ACL)},
    title = {Contrastive Decoding: Open-ended Text Generation as Optimization},
    year = {2023},
  }
  

  [bib] [paper]
  
• Backpack language models. John Hewitt, John Thickstun, Christopher D. Manning, Percy Liang. Association for Computational Linguistics (ACL), 2023. Outstanding paper award.

  @inproceedings{hewitt2023backpack,
    author = {John Hewitt and John Thickstun and Christopher D. Manning and Percy Liang},
    booktitle = {Association for Computational Linguistics (ACL)},
    title = {Backpack Language Models},
    year = {2023},
  }
  

  [bib] [paper]
  
• "No, to the right"-- online language corrections for robotic manipulation via shared autonomy. Yuchen Cui, Siddharth Karamcheti, Raj Palleti, Nidhya Shivakumar, Percy Liang, Dorsa Sadigh. ACM/IEEE International Conference on Human Robot Interaction (HRI), 2023.

  @inproceedings{cui2023corrections,
    author = {Yuchen Cui and Siddharth Karamcheti and Raj Palleti and Nidhya Shivakumar and Percy Liang and Dorsa Sadigh},
    booktitle = {ACM/IEEE International Conference on Human Robot Interaction (HRI)},
    title = {"No, to the Right"-- Online Language Corrections for Robotic Manipulation via Shared Autonomy},
    year = {2023},
  }
  

  [bib] [paper]
  
• Is a caption worth a thousand images? a controlled study for representation learning. Shibani Santurkar, Yann Dubois, Rohan Taori, Percy Liang, Tatsunori Hashimoto. International Conference on Learning Representations (ICLR), 2023.

  @inproceedings{santurkar2023captions,
    author = {Shibani Santurkar and Yann Dubois and Rohan Taori and Percy Liang and Tatsunori Hashimoto},
    booktitle = {International Conference on Learning Representations (ICLR)},
    title = {Is a Caption Worth a Thousand Images? A Controlled Study for Representation Learning},
    year = {2023},
  }
  

  [bib] [paper]
  
• Surgical fine-tuning improves adaptation to distribution shifts. Yoonho Lee, Annie S. Chen, Fahim Tajwar, Ananya Kumar, Huaxiu Yao, Percy Liang, Chelsea Finn. International Conference on Learning Representations (ICLR), 2023.

  @inproceedings{lee2023surgical,
    author = {Yoonho Lee and Annie S. Chen and Fahim Tajwar and Ananya Kumar and Huaxiu Yao and Percy Liang and Chelsea Finn},
    booktitle = {International Conference on Learning Representations (ICLR)},
    title = {Surgical Fine-Tuning Improves Adaptation to Distribution Shifts},
    year = {2023},
  }
  

  [bib] [paper]
  
• Holistic evaluation of language models. Percy Liang, Rishi Bommasani, Tony Lee, Dimitris Tsipras, Dilara Soylu, Michihiro Yasunaga, Yian Zhang, D. Narayanan, Yuhuai Wu, Ananya Kumar, Benjamin Newman, Binhang Yuan, Bobby Yan, Ce Zhang, Christian Cosgrove, Christopher D. Manning, Christopher Ré, Diana Acosta-Navas, Drew A. Hudson, E. Zelikman, Esin Durmus, Faisal Ladhak, Frieda Rong, Hongyu Ren, Huaxiu Yao, Jue Wang, Keshav Santhanam, Laurel J. Orr, Lucia Zheng, Mert Yuksekgonul, Mirac Suzgun, Nathan S. Kim, Neel Guha, Niladri S. Chatterji, O. Khattab, Peter Henderson, Qian Huang, Ryan Chi, Sang Michael Xie, Shibani Santurkar, S. Ganguli, Tatsunori Hashimoto, Thomas F. Icard, Tianyi Zhang, Vishrav Chaudhary, William Wang, Xuechen Li, Yifan Mai, Yuhui Zhang, Yuta Koreeda. Transcations of Machine Learning Research (TMLR), 2023.

  @article{liang2023helm,
    author = {Percy Liang and Rishi Bommasani and Tony Lee and Dimitris Tsipras and Dilara Soylu and Michihiro Yasunaga and Yian Zhang and D. Narayanan and Yuhuai Wu and Ananya Kumar and Benjamin Newman and Binhang Yuan and Bobby Yan and Ce Zhang and Christian Cosgrove and Christopher D. Manning and Christopher Ré and Diana Acosta-Navas and Drew A. Hudson and E. Zelikman and Esin Durmus and Faisal Ladhak and Frieda Rong and Hongyu Ren and Huaxiu Yao and Jue Wang and Keshav Santhanam and Laurel J. Orr and Lucia Zheng and Mert Yuksekgonul and Mirac Suzgun and Nathan S. Kim and Neel Guha and Niladri S. Chatterji and O. Khattab and Peter Henderson and Qian Huang and Ryan Chi and Sang Michael Xie and Shibani Santurkar and S. Ganguli and Tatsunori Hashimoto and Thomas F. Icard and Tianyi Zhang and Vishrav Chaudhary and William Wang and Xuechen Li and Yifan Mai and Yuhui Zhang and Yuta Koreeda},
    journal = {Transcations of Machine Learning Research (TMLR)},
    title = {Holistic Evaluation of Language Models},
    volume = {0},
    year = {2023},
  }
  

  [bib] [paper]
  

2022

• Truncation sampling as language model desmoothing. John Hewitt, Christopher D. Manning, Percy Liang. Findings of Empirical Methods in Natural Language Processing (Findings of EMNLP), 2022.

  @inproceedings{hewitt2022truncation,
    author = {John Hewitt and Christopher D. Manning and Percy Liang},
    booktitle = {Findings of Empirical Methods in Natural Language Processing (Findings of EMNLP)},
    title = {Truncation Sampling as Language Model Desmoothing},
    year = {2022},
  }
  

  [bib] [paper]
  
• Insights into pre-training via simpler synthetic tasks. Yuhuai Wu, Felix Li, Percy Liang. Advances in Neural Information Processing Systems (NeurIPS), 2022.

  @inproceedings{wu2022synthetic,
    author = {Yuhuai Wu and Felix Li and Percy Liang},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    title = {Insights into Pre-training via Simpler Synthetic Tasks},
    year = {2022},
  }
  

  [bib] [paper]
  
• Improving self-supervised learning by characterizing idealized representations. Yann Dubois, Tatsunori Hashimoto, S. Ermon, Percy Liang. Advances in Neural Information Processing Systems (NeurIPS), 2022.

  @inproceedings{dubois2022issl,
    author = {Yann Dubois and Tatsunori Hashimoto and S. Ermon and Percy Liang},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    title = {Improving Self-Supervised Learning by Characterizing Idealized Representations},
    year = {2022},
  }
  

  [bib] [paper]
  
• Decentralized training of foundation models in heterogeneous environments. Binhang Yuan, Yongjun He, Jared Quincy Davis, Tianyi Zhang, Tri Dao, Beidi Chen, Percy Liang, Christopher Re, Ce Zhang. Advances in Neural Information Processing Systems (NeurIPS), 2022.

  @inproceedings{yuan2022decentralized,
    author = {Binhang Yuan and Yongjun He and Jared Quincy Davis and Tianyi Zhang and Tri Dao and Beidi Chen and Percy Liang and Christopher Re and Ce Zhang},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    title = {Decentralized Training of Foundation Models in Heterogeneous Environments},
    year = {2022},
  }
  

  [bib] [paper]
  
• Diffusion-LM improves controllable text generation. Xiang Lisa Li, John Thickstun, Ishaan Gulrajani, Percy Liang, Tatsunori Hashimoto. Advances in Neural Information Processing Systems (NeurIPS), 2022.

  @inproceedings{li2022diffusion,
    author = {Xiang Lisa Li and John Thickstun and Ishaan Gulrajani and Percy Liang and Tatsunori Hashimoto},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    title = {Diffusion-{LM} Improves Controllable Text Generation},
    year = {2022},
  }
  

  [bib] [paper]
  
• What can transformers learn in-context? a case study of simple function classes. Shivam Garg, Dimitris Tsipras, Percy Liang, G. Valiant. Advances in Neural Information Processing Systems (NeurIPS), 2022.

  @inproceedings{garg2022incontext,
    author = {Shivam Garg and Dimitris Tsipras and Percy Liang and G. Valiant},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    title = {What Can Transformers Learn In-Context? A Case Study of Simple Function Classes},
    year = {2022},
  }
  

  [bib] [paper]
  
• Deep bidirectional language-knowledge graph pretraining. Michihiro Yasunaga, Antoine Bosselut, Hongyu Ren, Xikun Zhang, Christopher D. Manning, Percy Liang*, Jure Leskovec*. Advances in Neural Information Processing Systems (NeurIPS), 2022.

  @inproceedings{yasunaga2022dragon,
    author = {Michihiro Yasunaga and Antoine Bosselut and Hongyu Ren and Xikun Zhang and Christopher D. Manning and Percy Liang and Jure Leskovec},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    title = {Deep Bidirectional Language-Knowledge Graph Pretraining},
    year = {2022},
  }
  

  [bib] [paper]
  
• Picking on the same person: does algorithmic monoculture lead to outcome homogenization? Rishi Bommasani, Kathleen A. Creel, Ananya Kumar, Dan Jurafsky, Percy Liang. Advances in Neural Information Processing Systems (NeurIPS), 2022.

  @inproceedings{bommasani2022homogenization,
    author = {Rishi Bommasani and Kathleen A. Creel and Ananya Kumar and Dan Jurafsky and Percy Liang},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    title = {Picking on the Same Person: Does Algorithmic Monoculture lead to Outcome Homogenization?},
    year = {2022},
  }
  

  [bib] [paper]
  
• Melody transcription via generative pre-training. Chris Donahue, John Thickstun, Percy Liang. International Society for Music Information Retrieval (ISMIR), 2022.

  @inproceedings{donahue2022melody,
    author = {Chris Donahue and John Thickstun and Percy Liang},
    booktitle = {International Society for Music Information Retrieval (ISMIR)},
    title = {Melody transcription via generative pre-training},
    year = {2022},
  }
  

  [bib] [paper]
  
• Social simulacra: creating populated prototypes for social computing systems. J. Park, Lindsay Popowski, Carrie J. Cai, M. Morris, Percy Liang, Michael S. Bernstein. User Interface Software and Technology (UIST), 2022.

  @inproceedings{park2022social,
    author = {J. Park and Lindsay Popowski and Carrie J. Cai and M. Morris and Percy Liang and Michael S. Bernstein},
    booktitle = {User Interface Software and Technology (UIST)},
    title = {Social Simulacra: Creating Populated Prototypes for Social Computing Systems},
    year = {2022},
  }
  

  [bib] [paper]
  
• Emergent abilities of large language models. Jason Wei, Yi Tay, Rishi Bommasani, Colin Raffel, Barret Zoph, Sebastian Borgeaud, Dani Yogatama, Maarten Bosma, Denny Zhou, Donald Metzler, Ed Chi, Tatsunori Hashimoto, Oriol Vinyals, Percy Liang, Jeff Dean, William Fedus. Transcations of Machine Learning Research (TMLR), 2022.

  @article{wei2022emergent,
    author = {Jason Wei and Yi Tay and Rishi Bommasani and Colin Raffel and Barret Zoph and Sebastian Borgeaud and Dani Yogatama and Maarten Bosma and Denny Zhou and Donald Metzler and Ed Chi and Tatsunori Hashimoto and Oriol Vinyals and Percy Liang and Jeff Dean and William Fedus},
    journal = {Transcations of Machine Learning Research (TMLR)},
    title = {Emergent Abilities of Large Language Models},
    volume = {0},
    year = {2022},
  }
  

  [bib] [paper]
  
• Calibrated ensembles can mitigate accuracy tradeoffs under distribution shift. Ananya Kumar, Tengyu Ma, Percy Liang, Aditi Raghunathan. Uncertainty in Artificial Intelligence (UAI), 2022.

  @inproceedings{kumar2022calibrated,
    author = {Ananya Kumar and Tengyu Ma and Percy Liang and Aditi Raghunathan},
    booktitle = {Uncertainty in Artificial Intelligence (UAI)},
    title = {Calibrated ensembles can mitigate accuracy tradeoffs under distribution shift},
    year = {2022},
  }
  

  [bib] [paper]
  
• Shared autonomy for robotic manipulation with language corrections. Siddharth Karamcheti*, Raj Palleti*, Yuchen Cui, Percy Liang, Dorsa Sadigh. ACL Workshop for Learning with Natural Language Supervision (NL Supervision), 2022.

  @inproceedings{karamcheti2022lilac,
    author = {Siddharth Karamcheti and Raj Palleti and Yuchen Cui and Percy Liang and Dorsa Sadigh},
    booktitle = {ACL Workshop for Learning with Natural Language Supervision (NL Supervision)},
    title = {Shared Autonomy for Robotic Manipulation with Language Corrections},
    year = {2022},
  }
  

  [bib] [paper]
  
• Connect, not collapse: explaining contrastive learning for unsupervised domain adaptation. Kendrick Shen, Robbie Jones, Ananya Kumar, Sang Michael Xie, Jeff Z. HaoChen, Tengyu Ma, Percy Liang. International Conference on Machine Learning (ICML), 2022.

  @inproceedings{shen2022connect,
    author = {Kendrick Shen and Robbie Jones and Ananya Kumar and Sang Michael Xie and Jeff Z. HaoChen and Tengyu Ma and Percy Liang},
    booktitle = {International Conference on Machine Learning (ICML)},
    title = {Connect, Not Collapse: Explaining Contrastive Learning for Unsupervised Domain Adaptation},
    year = {2022},
  }
  

  [bib] [paper]
  
• LinkBERT: pretraining language models with document links. Michihiro Yasunaga, Jure Leskovec*, Percy Liang*. Association for Computational Linguistics (ACL), 2022.

  @inproceedings{yasunaga2022linkbert,
    author = {Michihiro Yasunaga and Jure Leskovec and Percy Liang},
    booktitle = {Association for Computational Linguistics (ACL)},
    title = {{LinkBERT}: Pretraining Language Models with Document Links},
    year = {2022},
  }
  

  [bib] [paper] [CodaLab]
  
• Extending the WILDS benchmark for unsupervised adaptation. Shiori Sagawa, Pang Wei Koh, Tony Lee, Irena Gao, Sang Michael Xie, Kendrick Shen, Ananya Kumar, Weihua Hu, Michihiro Yasunaga, H. Marklund, Sara Beery, E. David, I. Stavness, Wei Guo, J. Leskovec, Kate Saenko, Tatsunori B. Hashimoto, S. Levine, Chelsea Finn, Percy Liang. International Conference on Learning Representations (ICLR), 2022.

  @inproceedings{sagawa2022uwilds,
    author = {Shiori Sagawa and Pang Wei Koh and Tony Lee and Irena Gao and Sang Michael Xie and Kendrick Shen and Ananya Kumar and Weihua Hu and Michihiro Yasunaga and H. Marklund and Sara Beery and E. David and I. Stavness and Wei Guo and J. Leskovec and Kate Saenko and Tatsunori B. Hashimoto and S. Levine and Chelsea Finn and Percy Liang},
    booktitle = {International Conference on Learning Representations (ICLR)},
    title = {Extending the {WILDS} Benchmark for Unsupervised Adaptation},
    year = {2022},
  }
  

  [bib] [paper]
  
• Fine-tuning can distort pretrained features and underperform out-of-distribution. Ananya Kumar, Aditi Raghunathan, Robbie Jones, Tengyu Ma, Percy Liang. International Conference on Learning Representations (ICLR), 2022.

  @inproceedings{kumar2022finetuning,
    author = {Ananya Kumar and Aditi Raghunathan and Robbie Jones and Tengyu Ma and Percy Liang},
    booktitle = {International Conference on Learning Representations (ICLR)},
    title = {Fine-tuning can Distort Pretrained Features and Underperform Out-of-Distribution},
    year = {2022},
  }
  

  [bib] [paper] [CodaLab]
  
• An explanation of in-context learning as implicit Bayesian inference. Sang Michael Xie, Aditi Raghunathan, Percy Liang, Tengyu Ma. International Conference on Learning Representations (ICLR), 2022.

  @inproceedings{xie2022incontext,
    author = {Sang Michael Xie and Aditi Raghunathan and Percy Liang and Tengyu Ma},
    booktitle = {International Conference on Learning Representations (ICLR)},
    title = {An Explanation of In-context Learning as Implicit {B}ayesian Inference},
    year = {2022},
  }
  

  [bib] [paper] [CodaLab]
  
• Large language models can be strong differentially private learners. Xuechen Li, Florian Tramèr, Percy Liang, Tatsunori B. Hashimoto. International Conference on Learning Representations (ICLR), 2022.

  @inproceedings{li2022privacy,
    author = {Xuechen Li and Florian Tramèr and Percy Liang and Tatsunori B. Hashimoto},
    booktitle = {International Conference on Learning Representations (ICLR)},
    title = {Large Language Models Can Be Strong Differentially Private Learners},
    year = {2022},
  }
  

  [bib] [paper]
  
• GreaseLM: graph reasoning enhanced language models for question answering. Xikun Zhang, Antoine Bosselut, Michihiro Yasunaga, Hongyu Ren, Percy Liang, Christopher D. Manning, J. Leskovec. International Conference on Learning Representations (ICLR), 2022.

  @inproceedings{zhang2022greaselm,
    author = {Xikun Zhang and Antoine Bosselut and Michihiro Yasunaga and Hongyu Ren and Percy Liang and Christopher D. Manning and J. Leskovec},
    booktitle = {International Conference on Learning Representations (ICLR)},
    title = {GreaseLM: Graph REASoning Enhanced Language Models for Question Answering},
    year = {2022},
  }
  

  [bib] [paper]
  
• CoAuthor: designing a human-AI collaborative writing dataset for exploring language model capabilities. Mina Lee, Percy Liang, Qian Yang. Conference on Human Factors in Computing Systems (CHI), 2022. Honorable mention award.

  @inproceedings{lee2022coauthor,
    author = {Mina Lee and Percy Liang and Qian Yang},
    booktitle = {Conference on Human Factors in Computing Systems (CHI)},
    title = {Co{A}uthor: Designing a Human-{AI} Collaborative Writing Dataset for Exploring Language Model Capabilities},
    year = {2022},
  }
  

  [bib] [paper]
  

2021

• How does contrastive pre-training connect disparate domains? Kendrick Shen, Robbie Matthew Jones, Ananya Kumar, Sang Michael Xie, Percy Liang. NeurIPS Workshop on Distribution Shifts, 2021.

  @inproceedings{shen2021connect,
    author = {Kendrick Shen and Robbie Matthew Jones and Ananya Kumar and Sang Michael Xie and Percy Liang},
    booktitle = {NeurIPS Workshop on Distribution Shifts},
    title = {How Does Contrastive Pre-training Connect Disparate Domains?},
    year = {2021},
  }
  

  [bib]
  
• LILA: language-informed latent actions. Siddharth Karamcheti*, Megha Srivastava*, Percy Liang, Dorsa Sadigh. Conference on Robot Learning (CoRL), 2021.

  @inproceedings{karamcheti2021lila,
    author = {Siddharth Karamcheti and Megha Srivastava and Percy Liang and Dorsa Sadigh},
    booktitle = {Conference on Robot Learning (CoRL)},
    title = {{LILA}: Language-Informed Latent Actions},
    year = {2021},
  }
  

  [bib] [paper]
  
• On the opportunities and risks of foundation models. Rishi Bommasani, Drew A. Hudson, Ehsan Adeli, Russ Altman, Simran Arora, Sydney von Arx, Michael S. Bernstein, Jeannette Bohg, Antoine Bosselut, Emma Brunskill, Erik Brynjolfsson, Shyamal Buch, Dallas Card, Rodrigo Castellon, Niladri Chatterji, Annie Chen, Kathleen Creel, Jared Quincy Davis, Dorottya Demszky, Chris Donahue, Moussa Doumbouya, Esin Durmus, Stefano Ermon, John Etchemendy, Kawin Ethayarajh, Li Fei-Fei, Chelsea Finn, Trevor Gale, Lauren Gillespie, Karan Goel, Noah Goodman, Shelby Grossman, Neel Guha, Tatsunori Hashimoto, Peter Henderson, John Hewitt, Daniel E. Ho, Jenny Hong, Kyle Hsu, Jing Huang, Thomas Icard, Saahil Jain, Dan Jurafsky, Pratyusha Kalluri, Siddharth Karamcheti, Geoff Keeling, Fereshte Khani, Omar Khattab, Pang Wei Koh, Mark Krass, Ranjay Krishna, Rohith Kuditipudi, Ananya Kumar, Faisal Ladhak, Mina Lee, Tony Lee, Jure Leskovec, Isabelle Levent, Xiang Lisa Li, Xuechen Li, Tengyu Ma, Ali Malik, Christopher D. Manning, Suvir Mirchandani, Eric Mitchell, Zanele Munyikwa, Suraj Nair, Avanika Narayan, Deepak Narayanan, Ben Newman, Allen Nie, Juan Carlos Niebles, Hamed Nilforoshan, Julian Nyarko, Giray Ogut, Laurel Orr, Isabel Papadimitriou, Joon Sung Park, Chris Piech, Eva Portelance, Christopher Potts, Aditi Raghunathan, Rob Reich, Hongyu Ren, Frieda Rong, Yusuf Roohani, Camilo Ruiz, Jack Ryan, Christopher Ré, Dorsa Sadigh, Shiori Sagawa, Keshav Santhanam, Andy Shih, Krishnan Srinivasan, Alex Tamkin, Rohan Taori, Armin W. Thomas, Florian Tramèr, Rose E. Wang, William Wang, Bohan Wu, Jiajun Wu, Yuhuai Wu, Sang Michael Xie, Michihiro Yasunaga, Jiaxuan You, Matei Zaharia, Michael Zhang, Tianyi Zhang, Xikun Zhang, Yuhui Zhang, Lucia Zheng, Kaitlyn Zhou, Percy Liang. arXiv preprint arXiv:2108.07258, 2021.

  @article{bommasani2021opportunities,
    author = {Rishi Bommasani and Drew A. Hudson and Ehsan Adeli and Russ Altman and Simran Arora and Sydney von Arx and Michael S. Bernstein and Jeannette Bohg and Antoine Bosselut and Emma Brunskill and Erik Brynjolfsson and Shyamal Buch and Dallas Card and Rodrigo Castellon and Niladri Chatterji and Annie Chen and Kathleen Creel and Jared Quincy Davis and Dorottya Demszky and Chris Donahue and Moussa Doumbouya and Esin Durmus and Stefano Ermon and John Etchemendy and Kawin Ethayarajh and Li Fei-Fei and Chelsea Finn and Trevor Gale and Lauren Gillespie and Karan Goel and Noah Goodman and Shelby Grossman and Neel Guha and Tatsunori Hashimoto and Peter Henderson and John Hewitt and Daniel E. Ho and Jenny Hong and Kyle Hsu and Jing Huang and Thomas Icard and Saahil Jain and Dan Jurafsky and Pratyusha Kalluri and Siddharth Karamcheti and Geoff Keeling and Fereshte Khani and Omar Khattab and Pang Wei Koh and Mark Krass and Ranjay Krishna and Rohith Kuditipudi and Ananya Kumar and Faisal Ladhak and Mina Lee and Tony Lee and Jure Leskovec and Isabelle Levent and Xiang Lisa Li and Xuechen Li and Tengyu Ma and Ali Malik and Christopher D. Manning and Suvir Mirchandani and Eric Mitchell and Zanele Munyikwa and Suraj Nair and Avanika Narayan and Deepak Narayanan and Ben Newman and Allen Nie and Juan Carlos Niebles and Hamed Nilforoshan and Julian Nyarko and Giray Ogut and Laurel Orr and Isabel Papadimitriou and Joon Sung Park and Chris Piech and Eva Portelance and Christopher Potts and Aditi Raghunathan and Rob Reich and Hongyu Ren and Frieda Rong and Yusuf Roohani and Camilo Ruiz and Jack Ryan and Christopher Ré and Dorsa Sadigh and Shiori Sagawa and Keshav Santhanam and Andy Shih and Krishnan Srinivasan and Alex Tamkin and Rohan Taori and Armin W. Thomas and Florian Tramèr and Rose E. Wang and William Wang and Bohan Wu and Jiajun Wu and Yuhuai Wu and Sang Michael Xie and Michihiro Yasunaga and Jiaxuan You and Matei Zaharia and Michael Zhang and Tianyi Zhang and Xikun Zhang and Yuhui Zhang and Lucia Zheng and Kaitlyn Zhou and Percy Liang},
    journal = {arXiv preprint arXiv:2108.07258},
    title = {On the Opportunities and Risks of Foundation Models},
    year = {2021},
  }
  

  [bib] [paper]
  
• LM-Critic: language models for unsupervised grammatical error correction. Michihiro Yasunaga, Jure Leskovec, Percy Liang. Empirical Methods in Natural Language Processing (EMNLP), 2021.

  @inproceedings{yasunaga2021language,
    author = {Michihiro Yasunaga and Jure Leskovec and Percy Liang},
    booktitle = {Empirical Methods in Natural Language Processing (EMNLP)},
    title = {{LM-Critic}: Language Models for Unsupervised Grammatical Error Correction},
    year = {2021},
  }
  

  [bib] [paper] [CodaLab]
  
• Conditional probing: measuring usable information beyond a baseline. John Hewitt, Kawin Ethayarajh, Percy Liang, Christopher D. Manning. Empirical Methods in Natural Language Processing (EMNLP), 2021.

  @inproceedings{hewitt2021conditional,
    author = {John Hewitt and Kawin Ethayarajh and Percy Liang and Christopher D. Manning},
    booktitle = {Empirical Methods in Natural Language Processing (EMNLP)},
    title = {Conditional probing: measuring usable information beyond a baseline},
    year = {2021},
  }
  

  [bib] [paper] [CodaLab]
  
• Codified audio language modeling learns useful representations for music information retrieval. Rodrigo Castellon, Chris Donahue, Percy Liang. International Society for Music Information Retrieval (ISMIR), 2021. Best paper runner up.

  @inproceedings{castellon2021calm,
    author = {Rodrigo Castellon and Chris Donahue and Percy Liang},
    booktitle = {International Society for Music Information Retrieval (ISMIR)},
    title = {Codified audio language modeling learns useful representations for music information retrieval},
    year = {2021},
  }
  

  [bib] [paper] [CodaLab]
  
• Break-It-Fix-It: unsupervised learning for program repair. Michihiro Yasunaga, Percy Liang. International Conference on Machine Learning (ICML), 2021.

  @inproceedings{yasunaga2021break,
    author = {Michihiro Yasunaga and Percy Liang},
    booktitle = {International Conference on Machine Learning (ICML)},
    title = {{Break-It-Fix-It}: Unsupervised Learning for Program Repair},
    year = {2021},
  }
  

  [bib] [paper] [CodaLab]
  
• Catformer: designing stable transformers via sensitivity analysis. Jared Quincy Davis, Albert Gu, Krzysztof Choromanski, Tri Dao, Christopher Re, Chelsea Finn, Percy Liang. International Conference on Machine Learning (ICML), 2021.

  @inproceedings{davis2021catformer,
    author = {Jared Quincy Davis and Albert Gu and Krzysztof Choromanski and Tri Dao and Christopher Re and Chelsea Finn and Percy Liang},
    booktitle = {International Conference on Machine Learning (ICML)},
    title = {Catformer: Designing Stable Transformers via Sensitivity Analysis},
    year = {2021},
  }
  

  [bib] [paper]
  
• Just train twice: improving group robustness without training group information. Evan Zheran Liu, Behzad Haghgoo, Annie S. Chen, Aditi Raghunathan, Pang Wei Koh, Shiori Sagawa, Percy Liang, Chelsea Finn. International Conference on Machine Learning (ICML), 2021.

  @inproceedings{liu2021jtt,
    author = {Evan Zheran Liu and Behzad Haghgoo and Annie S. Chen and Aditi Raghunathan and Pang Wei Koh and Shiori Sagawa and Percy Liang and Chelsea Finn},
    booktitle = {International Conference on Machine Learning (ICML)},
    title = {Just Train Twice: Improving Group Robustness without Training Group Information},
    year = {2021},
  }
  

  [bib] [paper]
  
• Decoupling exploration and exploitation for meta-reinforcement learning without sacrifices. Evan Zheran Liu, Aditi Raghunathan, Percy Liang, Chelsea Finn. International Conference on Machine Learning (ICML), 2021.

  @inproceedings{liu2021dream,
    author = {Evan Zheran Liu and Aditi Raghunathan and Percy Liang and Chelsea Finn},
    booktitle = {International Conference on Machine Learning (ICML)},
    title = {Decoupling Exploration and Exploitation for Meta-Reinforcement Learning without Sacrifices},
    year = {2021},
  }
  

  [bib] [paper]
  
• Composed fine-tuning: freezing pre-trained denoising autoencoders for improved generalization. Sang Michael Xie, Tengyu Ma, Percy Liang. International Conference on Machine Learning (ICML), 2021.

  @inproceedings{xie2021composed,
    author = {Sang Michael Xie and Tengyu Ma and Percy Liang},
    booktitle = {International Conference on Machine Learning (ICML)},
    title = {Composed Fine-Tuning: Freezing Pre-Trained Denoising Autoencoders for Improved Generalization},
    year = {2021},
  }
  

  [bib] [paper] [CodaLab]
  
• WILDS: a benchmark of in-the-wild distribution shifts. Pang Wei Koh*, Shiori Sagawa*, Henrik Marklund, Sang Michael Xie, Marvin Zhang, Akshay Balsubramani, Weihua Hu, Michihiro Yasunaga, Richard Lanas Phillips, Irena Gao, Tony Lee, Etienne David, Ian Stavness, Wei Guo, Berton A. Earnshaw, Imran S. Haque, Sara Beery, Jure Leskovec, Anshul Kundaje, Emma Pierson, Sergey Levine, Chelsea Finn, Percy Liang. International Conference on Machine Learning (ICML), 2021.

  @inproceedings{koh2021wilds,
    author = {Pang Wei Koh and Shiori Sagawa and Henrik Marklund and Sang Michael Xie and Marvin Zhang and Akshay Balsubramani and Weihua Hu and Michihiro Yasunaga and Richard Lanas Phillips and Irena Gao and Tony Lee and Etienne David and Ian Stavness and Wei Guo and Berton A. Earnshaw and Imran S. Haque and Sara Beery and Jure Leskovec and Anshul Kundaje and Emma Pierson and Sergey Levine and Chelsea Finn and Percy Liang},
    booktitle = {International Conference on Machine Learning (ICML)},
    title = {{WILDS}: A Benchmark of in-the-Wild Distribution Shifts},
    year = {2021},
  }
  

  [bib] [paper]
  
• Accuracy on the line: on the strong correlation between out-of-distribution and in-distribution generalization. John Miller, Rohan Taori, Aditi Raghunathan, Shiori Sagawa, Pang Wei Koh, Vaishaal Shankar, Percy Liang, Yair Carmon, Ludwig Schmidt. International Conference on Machine Learning (ICML), 2021.

  @inproceedings{miller2021line,
    author = {John Miller and Rohan Taori and Aditi Raghunathan and Shiori Sagawa and Pang Wei Koh and Vaishaal Shankar and Percy Liang and Yair Carmon and Ludwig Schmidt},
    booktitle = {International Conference on Machine Learning (ICML)},
    title = {Accuracy on the Line: on the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization},
    year = {2021},
  }
  

  [bib] [paper]
  
• Swords: a benchmark for lexical substitution with improved data coverage and quality. Mina Lee, C. Donahue, Robin Jia, Alexander Iyabor, Percy Liang. North American Association for Computational Linguistics (NAACL), 2021.

  @inproceedings{lee2021swords,
    author = {Mina Lee and C. Donahue and Robin Jia and Alexander Iyabor and Percy Liang},
    booktitle = {North American Association for Computational Linguistics (NAACL)},
    title = {Swords: A Benchmark for Lexical Substitution with Improved Data Coverage and Quality},
    year = {2021},
  }
  

  [bib] [paper]
  
• QA-GNN: reasoning with language models and knowledge graphs for question answering. Michihiro Yasunaga, Hongyu Ren, Antoine Bosselut, Percy Liang, Jure Leskovec. North American Association for Computational Linguistics (NAACL), 2021.

  @inproceedings{yasunaga2021qagnn,
    author = {Michihiro Yasunaga and Hongyu Ren and Antoine Bosselut and Percy Liang and Jure Leskovec},
    booktitle = {North American Association for Computational Linguistics (NAACL)},
    title = {{QA-GNN}: Reasoning with Language Models and Knowledge Graphs for Question Answering},
    year = {2021},
  }
  

  [bib] [paper] [CodaLab]
  
• Prefix-Tuning: optimizing continuous prompts for generation. Xiang Lisa Li, Percy Liang. Association for Computational Linguistics (ACL), 2021.

  @inproceedings{li2021prefix,
    author = {Xiang Lisa Li and Percy Liang},
    booktitle = {Association for Computational Linguistics (ACL)},
    title = {Prefix-Tuning: Optimizing Continuous Prompts for Generation},
    year = {2021},
  }
  

  [bib] [paper]
  
• Selective classification can magnify disparities across groups. Erik Jones*, Shiori Sagawa*, Pang Wei Koh*, Ananya Kumar, Percy Liang. International Conference on Learning Representations (ICLR), 2021.

  @inproceedings{jones2021selective,
    author = {Erik Jones and Shiori Sagawa and Pang Wei Koh and Ananya Kumar and Percy Liang},
    booktitle = {International Conference on Learning Representations (ICLR)},
    title = {Selective Classification Can Magnify Disparities Across Groups},
    year = {2021},
  }
  

  [bib] [paper] [CodaLab]
  
• In-N-Out: pre-training and self-training using auxiliary information for out-of-distribution robustness. Sang Michael Xie*, Ananya Kumar*, Robbie Jones*, Fereshte Khani, Tengyu Ma, Percy Liang. International Conference on Learning Representations (ICLR), 2021.

  @inproceedings{xie2021innout,
    author = {Sang Michael Xie and Ananya Kumar and Robbie Jones and Fereshte Khani and Tengyu Ma and Percy Liang},
    booktitle = {International Conference on Learning Representations (ICLR)},
    title = {In-{N}-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness},
    year = {2021},
  }
  

  [bib] [paper] [CodaLab]
  
• Removing spurious features can hurt accuracy and affect groups disproportionately. Fereshte Khani, Percy Liang. ACM Conference on Fairness, Accountability, and Transparency (FAccT), 2021.

  @inproceedings{khani2021removing,
    author = {Fereshte Khani and Percy Liang},
    booktitle = {ACM Conference on Fairness, Accountability, and Transparency (FAccT)},
    title = {Removing Spurious Features can Hurt Accuracy and Affect Groups Disproportionately},
    year = {2021},
  }
  

  [bib] [paper]
  
• Beyond i.i.d.: three levels of generalization for question answering on knowledge bases. Yu Gu, Sue Kase, Michelle T. Vanni, Brian M. Sadler, Percy Liang, Xifeng Yan, Yu Su. World Wide Web (WWW), 2021.

  @inproceedings{gu2021beyond,
    author = {Yu Gu and Sue Kase and Michelle T. Vanni and Brian M. Sadler and Percy Liang and Xifeng Yan and Yu Su},
    booktitle = {World Wide Web (WWW)},
    title = {Beyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge Bases},
    year = {2021},
  }
  

  [bib] [paper]
  
• Stronger data poisoning attacks break data sanitization defenses. Pang Wei Koh*, Jacob Steinhardt*, Percy Liang. Machine Learning, 2021.

  @article{koh2021stronger,
    author = {Pang Wei Koh and Jacob Steinhardt and Percy Liang},
    journal = {Machine Learning},
    title = {Stronger Data Poisoning Attacks Break Data Sanitization Defenses},
    volume = {1},
    year = {2021},
  }
  

  [bib] [paper]
  

2020

• Learning adaptive language interfaces through decomposition. Siddharth Karamcheti, Dorsa Sadigh, Percy Liang. EMNLP Workshop for Interactive and Executable Semantic Parsing (IntEx-SemPar), 2020.

  @inproceedings{karamcheti2020decomposition,
    author = {Siddharth Karamcheti and Dorsa Sadigh and Percy Liang},
    booktitle = {EMNLP Workshop for Interactive and Executable Semantic Parsing (IntEx-SemPar)},
    title = {Learning Adaptive Language Interfaces through Decomposition},
    year = {2020},
  }
  

  [bib] [paper]
  
• Explore then execute: adapting without rewards via factorized meta-reinforcement learning. Evan Zheran Liu, Aditi Raghunathan, Percy Liang, Chelsea Finn. arXiv preprint arXiv:2008.02790, 2020.

  @article{liu2020explore,
    author = {Evan Zheran Liu and Aditi Raghunathan and Percy Liang and Chelsea Finn},
    journal = {arXiv preprint arXiv:2008.02790},
    title = {Explore then Execute: Adapting without Rewards via Factorized Meta-Reinforcement Learning},
    year = {2020},
  }
  

  [bib] [paper]
  
• Learning abstract models for strategic exploration and fast reward transfer. Evan Zheran Liu, Ramtin Keramati, Sudarshan Seshadri, Kelvin Guu, Panupong Pasupat, Emma Brunskill, Percy Liang. arXiv preprint arXiv:2007.05896, 2020.

  @article{liu2020learning,
    author = {Evan Zheran Liu and Ramtin Keramati and Sudarshan Seshadri and Kelvin Guu and Panupong Pasupat and Emma Brunskill and Percy Liang},
    journal = {arXiv preprint arXiv:2007.05896},
    title = {Learning Abstract Models for Strategic Exploration and Fast Reward Transfer},
    year = {2020},
  }
  

  [bib] [paper]
  
• On the importance of adaptive data collection for extremely imbalanced pairwise tasks. Stephen Mussmann*, Robin Jia*, Percy Liang. Findings of Empirical Methods in Natural Language Processing (Findings of EMNLP), 2020.

  @inproceedings{mussmann2020pairwise,
    author = {Stephen Mussmann and Robin Jia and Percy Liang},
    booktitle = {Findings of Empirical Methods in Natural Language Processing (Findings of EMNLP)},
    title = {On the Importance of Adaptive Data Collection for Extremely Imbalanced Pairwise Tasks},
    year = {2020},
  }
  

  [bib] [paper] [CodaLab]
  
• RNNs can generate bounded hierarchical languages with optimal memory. John Hewitt, Michael Hahn, Surya Ganguli, Percy Liang, Christopher D. Manning. Empirical Methods in Natural Language Processing (EMNLP), 2020.

  @inproceedings{hewitt2020rnn,
    author = {John Hewitt and Michael Hahn and Surya Ganguli and Percy Liang and Christopher D. Manning},
    booktitle = {Empirical Methods in Natural Language Processing (EMNLP)},
    title = {{RNN}s can generate bounded hierarchical languages with optimal memory},
    year = {2020},
  }
  

  [bib] [paper] [CodaLab]
  
• The EOS decision and length extrapolation. Benjamin Newman, John Hewitt, Percy Liang, Christopher D. Manning. Proceedings of the Third BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, 2020. Outstanding paper award.

  @inproceedings{newman2020eos,
    author = {Benjamin Newman and John Hewitt and Percy Liang and Christopher D. Manning},
    booktitle = {Proceedings of the Third BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP},
    title = {The {EOS} Decision and Length Extrapolation},
    year = {2020},
  }
  

  [bib] [paper]
  
• Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming. Sumanth Dathathri*, Krishnamurthy Dvijotham*, Alexey Kurakin*, Aditi Raghunathan*, Jonathan Uesato*, Rudy Bunel, Shreya Shankar, Jacob Steinhardt, Ian Goodfellow, Percy Liang, Pushmeet Kohli. Advances in Neural Information Processing Systems (NeurIPS), 2020.

  @inproceedings{dathathri2020sdp,
    author = {Sumanth Dathathri and Krishnamurthy Dvijotham and Alexey Kurakin and Aditi Raghunathan and Jonathan Uesato and Rudy Bunel and Shreya Shankar and Jacob Steinhardt and Ian Goodfellow and Percy Liang and Pushmeet Kohli},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    title = {Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming},
    year = {2020},
  }
  

  [bib] [paper] [CodaLab]
  
• Task-Oriented dialogue as dataflow synthesis. Semantic Machines, Jacob Andreas, John Bufe, David Burkett, Charles Chen, Josh Clausman, Jean Crawford, Kate Crim, Jordan DeLoach, Leah Dorner, Jason Eisner, Hao Fang, Alan Guo, David Hall, Kristin Hayes, Kellie Hill, Diana Ho, Wendy Iwaszuk, Smriti Jha, Dan Klein, Jayant Krishnamurthy, Theo Lanman, Percy Liang, Christopher H. Lin, Ilya Lintsbakh, Andy McGovern, Aleksandr Nisnevich, Adam Pauls, Dmitrij Petters, Brent Read, Dan Roth, Subhro Roy, Jesse Rusak, Beth Short, Div Slomin, Ben Snyder, Stephon Striplin, Yu Su, Zachary Tellman, Sam Thomson, Andrei Vorobev, Izabela Witoszko, Jason Wolfe, Abby Wray, Yuchen Zhang, Alexander Zotov. Transactions of the Association for Computational Linguistics (TACL), 2020.

  @article{semanticmachines2020dataflow,
    author = {Semantic Machines and Jacob Andreas and John Bufe and David Burkett and Charles Chen and Josh Clausman and Jean Crawford and Kate Crim and Jordan DeLoach and Leah Dorner and Jason Eisner and Hao Fang and Alan Guo and David Hall and Kristin Hayes and Kellie Hill and Diana Ho and Wendy Iwaszuk and Smriti Jha and Dan Klein and Jayant Krishnamurthy and Theo Lanman and Percy Liang and Christopher H. Lin and Ilya Lintsbakh and Andy McGovern and Aleksandr Nisnevich and Adam Pauls and Dmitrij Petters and Brent Read and Dan Roth and Subhro Roy and Jesse Rusak and Beth Short and Div Slomin and Ben Snyder and Stephon Striplin and Yu Su and Zachary Tellman and Sam Thomson and Andrei Vorobev and Izabela Witoszko and Jason Wolfe and Abby Wray and Yuchen Zhang and Alexander Zotov},
    journal = {Transactions of the Association for Computational Linguistics (TACL)},
    title = {Task-Oriented Dialogue as Dataflow Synthesis},
    volume = {8},
    year = {2020},
  }
  

  [bib] [paper]
  
• An investigation of why overparameterization exacerbates spurious correlations. Shiori Sagawa*, Aditi Raghunathan*, Pang Wei Koh*, Percy Liang. International Conference on Machine Learning (ICML), 2020.

  @inproceedings{sagawa2020overparameterization,
    author = {Shiori Sagawa and Aditi Raghunathan and Pang Wei Koh and Percy Liang},
    booktitle = {International Conference on Machine Learning (ICML)},
    title = {An investigation of why overparameterization exacerbates spurious correlations},
    year = {2020},
  }
  

  [bib] [paper]
  
• Concept bottleneck models. Pang Wei Koh*, Thao Nguyen*, Yew Siang Tang*, Stephen Mussmann, Emma Pierson, Been Kim, Percy Liang. International Conference on Machine Learning (ICML), 2020.

  @inproceedings{koh2020bottleneck,
    author = {Pang Wei Koh and Thao Nguyen and Yew Siang Tang and Stephen Mussmann and Emma Pierson and Been Kim and Percy Liang},
    booktitle = {International Conference on Machine Learning (ICML)},
    title = {Concept Bottleneck Models},
    year = {2020},
  }
  

  [bib] [paper] [CodaLab]
  
• Feature noise induces loss discrepancy across groups. Fereshte Khani, Percy Liang. International Conference on Machine Learning (ICML), 2020.

  @inproceedings{khani2020noise,
    author = {Fereshte Khani and Percy Liang},
    booktitle = {International Conference on Machine Learning (ICML)},
    title = {Feature Noise Induces Loss Discrepancy Across Groups},
    year = {2020},
  }
  

  [bib] [paper] [CodaLab]
  
• Graph-based, self-supervised program repair from diagnostic feedback. Michihiro Yasunaga, Percy Liang. International Conference on Machine Learning (ICML), 2020.

  @inproceedings{yasunaga2020repair,
    author = {Michihiro Yasunaga and Percy Liang},
    booktitle = {International Conference on Machine Learning (ICML)},
    title = {Graph-based, Self-Supervised Program Repair from Diagnostic Feedback},
    year = {2020},
  }
  

  [bib] [paper] [CodaLab]
  
• Understanding and mitigating the tradeoff between robustness and accuracy. Aditi Raghunathan*, Sang Michael Xie*, Fanny Yang, John C. Duchi, Percy Liang. International Conference on Machine Learning (ICML), 2020.

  @inproceedings{raghunathan2020understanding,
    author = {Aditi Raghunathan and Sang Michael Xie and Fanny Yang and John C. Duchi and Percy Liang},
    booktitle = {International Conference on Machine Learning (ICML)},
    title = {Understanding and Mitigating the Tradeoff Between Robustness and Accuracy},
    year = {2020},
  }
  

  [bib] [paper]
  
• Understanding self-training for gradual domain adaptation. Ananya Kumar, Tengyu Ma, Percy Liang. International Conference on Machine Learning (ICML), 2020.

  @inproceedings{kumar2020gradual,
    author = {Ananya Kumar and Tengyu Ma and Percy Liang},
    booktitle = {International Conference on Machine Learning (ICML)},
    title = {Understanding Self-Training for Gradual Domain Adaptation},
    year = {2020},
  }
  

  [bib] [paper]
  
• Robustness to spurious correlations via human annotations. Megha Srivastava, Tatsunori Hashimoto, Percy Liang. International Conference on Machine Learning (ICML), 2020.

  @inproceedings{srivasta2020human,
    author = {Megha Srivastava and Tatsunori Hashimoto and Percy Liang},
    booktitle = {International Conference on Machine Learning (ICML)},
    title = {Robustness to Spurious Correlations via Human Annotations},
    year = {2020},
  }
  

  [bib] [paper] [CodaLab]
  
• Robust encodings: a framework for combating adversarial typos. Erik Jones, Robin Jia*, Aditi Raghunathan*, Percy Liang. Association for Computational Linguistics (ACL), 2020.

  @inproceedings{jones2020roben,
    author = {Erik Jones and Robin Jia and Aditi Raghunathan and Percy Liang},
    booktitle = {Association for Computational Linguistics (ACL)},
    title = {Robust Encodings: A Framework for Combating Adversarial Typos},
    year = {2020},
  }
  

  [bib] [paper] [CodaLab]
  
• Selective question answering under domain shift. Amita Kamath, Robin Jia, Percy Liang. Association for Computational Linguistics (ACL), 2020.

  @inproceedings{kamath2020squads,
    author = {Amita Kamath and Robin Jia and Percy Liang},
    booktitle = {Association for Computational Linguistics (ACL)},
    title = {Selective Question Answering under Domain Shift},
    year = {2020},
  }
  

  [bib] [paper] [CodaLab]
  
• Shaping visual representations with language for few-shot classification. Jesse Mu, Percy Liang, Noah Goodman. Association for Computational Linguistics (ACL), 2020. Short paper.

  @inproceedings{mu2020shaping,
    author = {Jesse Mu and Percy Liang and Noah Goodman},
    booktitle = {Association for Computational Linguistics (ACL)},
    title = {Shaping Visual Representations with Language for Few-shot Classification},
    year = {2020},
  }
  

  [bib] [paper] [CodaLab]
  
• ExpBERT: representation engineering with natural language explanations. Shikhar Murty, Pang Wei Koh, Percy Liang. Association for Computational Linguistics (ACL), 2020. Short paper.

  @inproceedings{murty2020expbert,
    author = {Shikhar Murty and Pang Wei Koh and Percy Liang},
    booktitle = {Association for Computational Linguistics (ACL)},
    title = {{ExpBERT}: Representation Engineering with Natural Language Explanations},
    year = {2020},
  }
  

  [bib] [paper] [CodaLab]
  
• Enabling language models to fill in the blanks. Chris Donahue, Mina Lee, Percy Liang. Association for Computational Linguistics (ACL), 2020. Short paper.

  @inproceedings{donahue2020infilling,
    author = {Chris Donahue and Mina Lee and Percy Liang},
    booktitle = {Association for Computational Linguistics (ACL)},
    title = {Enabling Language Models to Fill in the Blanks},
    year = {2020},
  }
  

  [bib] [paper]
  
• Distributionally robust neural networks for group shifts: on the importance of regularization for worst-case generalization. Shiori Sagawa*, Pang Wei Koh*, Tatsunori B. Hashimoto, Percy Liang. International Conference on Learning Representations (ICLR), 2020.

  @inproceedings{sagawa2020group,
    author = {Shiori Sagawa and Pang Wei Koh and Tatsunori B. Hashimoto and Percy Liang},
    booktitle = {International Conference on Learning Representations (ICLR)},
    title = {Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization},
    year = {2020},
  }
  

  [bib] [paper]
  
• Strategies for pre-training graph neural networks. Weihua Hu, Bowen Liu, Joseph Gomes, Marinka Zitnik, Percy Liang, Vijay Pande, Jure Leskovec. International Conference on Learning Representations (ICLR), 2020.

  @inproceedings{hu2020pretraining,
    author = {Weihua Hu and Bowen Liu and Joseph Gomes and Marinka Zitnik and Percy Liang and Vijay Pande and Jure Leskovec},
    booktitle = {International Conference on Learning Representations (ICLR)},
    title = {Strategies for Pre-training Graph Neural Networks},
    year = {2020},
  }
  

  [bib] [paper]
  
• Selection via proxy: efficient data selection for deep learning. Cody Coleman, Christopher Yeh, Stephen Mussmann, Baharan Mirzasoleiman, Peter Bailis, Percy Liang, Jure Leskovec, Matei Zaharia. International Conference on Learning Representations (ICLR), 2020.

  @inproceedings{coleman2020selection,
    author = {Cody Coleman and Christopher Yeh and Stephen Mussmann and Baharan Mirzasoleiman and Peter Bailis and Percy Liang and Jure Leskovec and Matei Zaharia},
    booktitle = {International Conference on Learning Representations (ICLR)},
    title = {Selection via Proxy: Efficient Data Selection for Deep Learning},
    year = {2020},
  }
  

  [bib] [paper]
  
• A tight analysis of greedy yields subexponential time approximation for uniform decision tree. Ray Li, Percy Liang, Stephen Mussmann. Symposium on Discrete Algorithms (SODA), 2020.

  @inproceedings{li2020greedy,
    author = {Ray Li and Percy Liang and Stephen Mussmann},
    booktitle = {Symposium on Discrete Algorithms (SODA)},
    title = {A Tight Analysis of Greedy Yields Subexponential Time Approximation for Uniform Decision Tree},
    year = {2020},
  }
  

  [bib] [paper]
  

2019

• Certified robustness to adversarial word substitutions. Robin Jia, Aditi Raghunathan, Kerem Göksel, Percy Liang. Empirical Methods in Natural Language Processing (EMNLP), 2019.

  @inproceedings{jia2019certified,
    author = {Robin Jia and Aditi Raghunathan and Kerem Göksel and Percy Liang},
    booktitle = {Empirical Methods in Natural Language Processing (EMNLP)},
    title = {Certified Robustness to Adversarial Word Substitutions},
    year = {2019},
  }
  

  [bib] [paper] [CodaLab]
  
• Distributionally robust language modeling. Yonatan Oren*, Shiori Sagawa*, Tatsunori Hashimoto*, Percy Liang. Empirical Methods in Natural Language Processing (EMNLP), 2019.

  @inproceedings{oren2019drolm,
    author = {Yonatan Oren and Shiori Sagawa and Tatsunori Hashimoto and Percy Liang},
    booktitle = {Empirical Methods in Natural Language Processing (EMNLP)},
    title = {Distributionally Robust Language Modeling},
    year = {2019},
  }
  

  [bib] [paper] [CodaLab]
  
• Designing and interpreting probes with control tasks. John Hewitt, Percy Liang. Empirical Methods in Natural Language Processing (EMNLP), 2019. Best paper runner up.

  @inproceedings{hewitt2019control,
    author = {John Hewitt and Percy Liang},
    booktitle = {Empirical Methods in Natural Language Processing (EMNLP)},
    title = {Designing and Interpreting Probes with Control Tasks},
    year = {2019},
  }
  

  [bib] [paper] [CodaLab]
  
• SPoC: search-based pseudocode to code. Sumith Kulal, Panupong Pasupat, Kartik Chandra, Mina Lee, Oded Padon, Alex Aiken, Percy Liang. Advances in Neural Information Processing Systems (NeurIPS), 2019.

  @inproceedings{kulal2019spoc,
    author = {Sumith Kulal and Panupong Pasupat and Kartik Chandra and Mina Lee and Oded Padon and Alex Aiken and Percy Liang},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    title = {SPoC: Search-based Pseudocode to Code},
    year = {2019},
  }
  

  [bib] [paper]
  
• Unlabeled data improves adversarial robustness. Yair Carmon*, Aditi Raghunathan*, Ludwig Schmidt, Percy Liang, John C. Duchi. Advances in Neural Information Processing Systems (NeurIPS), 2019.

  @inproceedings{carmon2019unlabeled,
    author = {Yair Carmon and Aditi Raghunathan and Ludwig Schmidt and Percy Liang and John C. Duchi},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    title = {Unlabeled Data Improves Adversarial Robustness},
    year = {2019},
  }
  

  [bib] [paper] [CodaLab]
  
• Verified uncertainty calibration. Ananya Kumar, Percy Liang, Tengyu Ma. Advances in Neural Information Processing Systems (NeurIPS), 2019.

  @inproceedings{kumar2019calibration,
    author = {Ananya Kumar and Percy Liang and Tengyu Ma},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    title = {Verified Uncertainty Calibration},
    year = {2019},
  }
  

  [bib] [paper] [CodaLab]
  
• On the accuracy of influence functions for measuring group effects. Pang Wei Koh*, Kai-Siang Ang*, Hubert H. K. Teo*, Percy Liang. Advances in Neural Information Processing Systems (NeurIPS), 2019.

  @inproceedings{koh2019influence,
    author = {Pang Wei Koh and Kai-Siang Ang and Hubert H. K. Teo and Percy Liang},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    title = {On the Accuracy of Influence Functions for Measuring Group Effects},
    year = {2019},
  }
  

  [bib] [paper] [CodaLab]
  
• Learning autocomplete systems as a communication game. Mina Lee, Tatsunori Hashimoto, Percy Liang. Emergent Communication Workshop at Neural Information Processing Systems (NeurIPS), 2019.

  @inproceedings{lee2019autocomplete,
    author = {Mina Lee and Tatsunori Hashimoto and Percy Liang},
    booktitle = {Emergent Communication Workshop at Neural Information Processing Systems (NeurIPS)},
    title = {Learning Autocomplete Systems as a Communication Game},
    year = {2019},
  }
  

  [bib] [paper] [CodaLab]
  
• Adversarial training can hurt generalization. Aditi Raghunathan*, Sang Michael Xie*, Fanny Yang, John C. Duchi, Percy Liang. arXiv preprint arXiv:1906.06032, 2019.

  @article{raghunathan2019hurt,
    author = {Aditi Raghunathan and Sang Michael Xie and Fanny Yang and John C. Duchi and Percy Liang},
    journal = {arXiv preprint arXiv:1906.06032},
    title = {Adversarial Training Can Hurt Generalization},
    year = {2019},
  }
  

  [bib] [paper]
  
• Maximum weighted loss discrepancy. Fereshte Khani, Aditi Raghunathan, Percy Liang. arXiv preprint arXiv:1906.03518, 2019.

  @article{khani2019mwld,
    author = {Fereshte Khani and Aditi Raghunathan and Percy Liang},
    journal = {arXiv preprint arXiv:1906.03518},
    title = {Maximum Weighted Loss Discrepancy},
    year = {2019},
  }
  

  [bib] [paper] [CodaLab]
  
• Ambitious data science can be painless. Hatef Monajemi, Riccardo Murri, Eric Jonas, Percy Liang, Victoria Stodden, David L. Donoho. Harvard Data Science Review, 2019.

  @article{monajemi2019painless,
    author = {Hatef Monajemi and Riccardo Murri and Eric Jonas and Percy Liang and Victoria Stodden and David L. Donoho},
    journal = {Harvard Data Science Review},
    title = {Ambitious Data Science Can Be Painless},
    volume = {1},
    year = {2019},
  }
  

  [bib] [paper]
  
• Unifying human and statistical evaluation for natural language generation. Tatsunori Hashimoto*, Hugh Zhang*, Percy Liang. North American Association for Computational Linguistics (NAACL), 2019.

  @inproceedings{hashimoto2019huse,
    author = {Tatsunori Hashimoto and Hugh Zhang and Percy Liang},
    booktitle = {North American Association for Computational Linguistics (NAACL)},
    title = {Unifying Human and Statistical Evaluation for Natural Language Generation},
    year = {2019},
  }
  

  [bib] [paper] [CodaLab]
  
• Pun generation with surprise. Nanyun Peng*, He He*, Percy Liang. North American Association for Computational Linguistics (NAACL), 2019.

  @inproceedings{peng2019pun,
    author = {Nanyun Peng and He He and Percy Liang},
    booktitle = {North American Association for Computational Linguistics (NAACL)},
    title = {Pun Generation with Surprise},
    year = {2019},
  }
  

  [bib] [paper] [CodaLab]
  
• Learning a SAT solver from single-bit supervision. Daniel Selsam, Matthew Lamm, Benedikt Bünz, Percy Liang, Leonardo de Moura, David L. Dill. International Conference on Learning Representations (ICLR), 2019.

  @inproceedings{selsam2019sat,
    author = {Daniel Selsam and Matthew Lamm and Benedikt Bünz and Percy Liang and Leonardo de Moura and David L. Dill},
    booktitle = {International Conference on Learning Representations (ICLR)},
    title = {Learning a {SAT} Solver from Single-Bit Supervision},
    year = {2019},
  }
  

  [bib] [paper]
  
• Defending against whitebox adversarial attacks via randomized discretization. Yuchen Zhang, Percy Liang. Artificial Intelligence and Statistics (AISTATS), 2019.

  @inproceedings{zhang2019discretization,
    author = {Yuchen Zhang and Percy Liang},
    booktitle = {Artificial Intelligence and Statistics (AISTATS)},
    title = {Defending against Whitebox Adversarial Attacks via Randomized Discretization},
    year = {2019},
  }
  

  [bib] [paper] [CodaLab]
  
• Inferring multidimensional rates of aging from cross-sectional data. Emma Pierson, Pang Wei Koh, Tatsunori Hashimoto, Daphne Koller, Jure Leskovec, Nick Eriksson, Percy Liang. Artificial Intelligence and Statistics (AISTATS), 2019.

  @inproceedings{pierson2019aging,
    author = {Emma Pierson and Pang Wei Koh and Tatsunori Hashimoto and Daphne Koller and Jure Leskovec and Nick Eriksson and Percy Liang},
    booktitle = {Artificial Intelligence and Statistics (AISTATS)},
    title = {Inferring Multidimensional Rates of Aging from Cross-Sectional Data},
    year = {2019},
  }
  

  [bib] [paper]
  
• FrAngel: component-based synthesis with control structures. Kensen Shi, Jacob Steinhardt, Percy Liang. Principles of Programming Languages (POPL), 2019.

  @inproceedings{shi2019frangel,
    author = {Kensen Shi and Jacob Steinhardt and Percy Liang},
    booktitle = {Principles of Programming Languages (POPL)},
    title = {{F}r{A}ngel: Component-Based Synthesis with Control Structures},
    year = {2019},
  }
  

  [bib] [paper] [CodaLab]
  

2018

• Semidefinite relaxations for certifying robustness to adversarial examples. Aditi Raghunathan, Jacob Steinhardt, Percy Liang. Advances in Neural Information Processing Systems (NeurIPS), 2018.

  @inproceedings{raghunathan2018sdp,
    author = {Aditi Raghunathan and Jacob Steinhardt and Percy Liang},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    title = {Semidefinite relaxations for certifying robustness to adversarial examples},
    year = {2018},
  }
  

  [bib] [paper]
  
• Uncertainty sampling is preconditioned stochastic gradient descent on zero-one loss. Stephen Mussmann, Percy Liang. Advances in Neural Information Processing Systems (NeurIPS), 2018.

  @inproceedings{mussmann2018sgd,
    author = {Stephen Mussmann and Percy Liang},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    title = {Uncertainty Sampling is Preconditioned Stochastic Gradient Descent on Zero-One Loss},
    year = {2018},
  }
  

  [bib] [paper] [CodaLab]
  
• A retrieve-and-edit framework for predicting structured outputs. Tatsunori Hashimoto, Kelvin Guu, Yonatan Oren, Percy Liang. Advances in Neural Information Processing Systems (NeurIPS), 2018.

  @inproceedings{hashimoto2018edit,
    author = {Tatsunori Hashimoto and Kelvin Guu and Yonatan Oren and Percy Liang},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    title = {A Retrieve-and-Edit Framework for Predicting Structured Outputs},
    year = {2018},
  }
  

  [bib] [paper] [CodaLab]
  
• QuAC: question answering in context. Eunsol Choi, He He, Mohit Iyyer, Mark Yatskar, Wen-tau Yih, Yejin Choi, Percy Liang, Luke Zettlemoyer. Empirical Methods in Natural Language Processing (EMNLP), 2018.

  @inproceedings{choi2018quac,
    author = {Eunsol Choi and He He and Mohit Iyyer and Mark Yatskar and Wen-tau Yih and Yejin Choi and Percy Liang and Luke Zettlemoyer},
    booktitle = {Empirical Methods in Natural Language Processing (EMNLP)},
    title = {{QuAC}: Question Answering in Context},
    year = {2018},
  }
  

  [bib] [paper]
  
• Decoupling strategy and generation in negotiation dialogues. He He, Derek Chen, Anusha Balakrishnan, Percy Liang. Empirical Methods in Natural Language Processing (EMNLP), 2018.

  @inproceedings{he2018negotiation,
    author = {He He and Derek Chen and Anusha Balakrishnan and Percy Liang},
    booktitle = {Empirical Methods in Natural Language Processing (EMNLP)},
    title = {Decoupling Strategy and Generation in Negotiation Dialogues},
    year = {2018},
  }
  

  [bib] [paper] [CodaLab]
  
• Mapping natural language commands to web elements. Panupong Pasupat, Tian-Shun Jiang, Evan Zheran Liu, Kelvin Guu, Percy Liang. Empirical Methods in Natural Language Processing (EMNLP), 2018. Short paper.

  @inproceedings{pasupat2018elements,
    author = {Panupong Pasupat and Tian-Shun Jiang and Evan Zheran Liu and Kelvin Guu and Percy Liang},
    booktitle = {Empirical Methods in Natural Language Processing (EMNLP)},
    title = {Mapping Natural Language Commands to Web Elements},
    year = {2018},
  }
  

  [bib] [paper] [CodaLab]
  
• Textual analogy parsing: what's shared and what's compared among analogous facts. Matthew Lamm, Arun Chaganty, Christopher D. Manning, Dan Jurafsky, Percy Liang. Empirical Methods in Natural Language Processing (EMNLP), 2018.

  @inproceedings{lamm2018tap,
    author = {Matthew Lamm and Arun Chaganty and Christopher D. Manning and Dan Jurafsky and Percy Liang},
    booktitle = {Empirical Methods in Natural Language Processing (EMNLP)},
    title = {Textual Analogy Parsing: What's Shared and What's Compared among Analogous Facts},
    year = {2018},
  }
  

  [bib] [paper]
  
• On the relationship between data efficiency and error in active learning. Stephen Mussmann, Percy Liang. International Conference on Machine Learning (ICML), 2018.

  @inproceedings{mussmann2018accuracy,
    author = {Stephen Mussmann and Percy Liang},
    booktitle = {International Conference on Machine Learning (ICML)},
    title = {On the Relationship between Data Efficiency and Error in Active Learning},
    year = {2018},
  }
  

  [bib] [paper] [CodaLab]
  
• Fairness without demographics in repeated loss minimization. Tatsunori B. Hashimoto, Megha Srivastava, Hongseok Namkoong, Percy Liang. International Conference on Machine Learning (ICML), 2018. Best paper runner up.

  @inproceedings{hashimoto2018repeated,
    author = {Tatsunori B. Hashimoto and Megha Srivastava and Hongseok Namkoong and Percy Liang},
    booktitle = {International Conference on Machine Learning (ICML)},
    title = {Fairness Without Demographics in Repeated Loss Minimization},
    year = {2018},
  }
  

  [bib] [paper] [CodaLab]
  
• Training classifiers with natural language explanations. Braden Hancock, Paroma Varma, Stephanie Wang, Martin Bringmann, Percy Liang, Christopher Ré. Association for Computational Linguistics (ACL), 2018.

  @inproceedings{hancock2018babble,
    author = {Braden Hancock and Paroma Varma and Stephanie Wang and Martin Bringmann and Percy Liang and Christopher Ré},
    booktitle = {Association for Computational Linguistics (ACL)},
    title = {Training Classifiers with Natural Language Explanations},
    year = {2018},
  }
  

  [bib] [paper] [CodaLab]
  
• The price of debiasing automatic metrics in natural language evaluation. Arun Chaganty, Stephen Mussmann, Percy Liang. Association for Computational Linguistics (ACL), 2018.

  @inproceedings{chaganty2018evaluation,
    author = {Arun Chaganty and Stephen Mussmann and Percy Liang},
    booktitle = {Association for Computational Linguistics (ACL)},
    title = {The price of debiasing automatic metrics in natural language evaluation},
    year = {2018},
  }
  

  [bib] [paper] [CodaLab]
  
• Know what you don't know: unanswerable questions for SQuAD. Pranav Rajpurkar, Robin Jia, Percy Liang. Association for Computational Linguistics (ACL), 2018. Best short paper award.

  @inproceedings{rajpurkar2018squadrun,
    author = {Pranav Rajpurkar and Robin Jia and Percy Liang},
    booktitle = {Association for Computational Linguistics (ACL)},
    title = {Know What You Don't Know: Unanswerable Questions for {SQuAD}},
    year = {2018},
  }
  

  [bib] [paper] [CodaLab]
  
• Generalized binary search for split-neighborly problems. Stephen Mussmann, Percy Liang. Artificial Intelligence and Statistics (AISTATS), 2018.

  @inproceedings{mussmann2018gbs,
    author = {Stephen Mussmann and Percy Liang},
    booktitle = {Artificial Intelligence and Statistics (AISTATS)},
    title = {Generalized Binary Search For Split-Neighborly Problems},
    year = {2018},
  }
  

  [bib] [paper]
  
• Planning, inference and pragmatics in sequential language games. Fereshte Khani, Noah D. Goodman, Percy Liang. Transactions of the Association for Computational Linguistics (TACL), 2018.

  @article{khani2018pip,
    author = {Fereshte Khani and Noah D. Goodman and Percy Liang},
    journal = {Transactions of the Association for Computational Linguistics (TACL)},
    title = {Planning, Inference and Pragmatics in Sequential Language Games},
    volume = {6},
    year = {2018},
  }
  

  [bib] [paper] [CodaLab]
  
• Generating sentences by editing prototypes. Kelvin Guu, Tatsunori B. Hashimoto, Yonatan Oren, Percy Liang. Transactions of the Association for Computational Linguistics (TACL), 2018.

  @article{guu2018edit,
    author = {Kelvin Guu and Tatsunori B. Hashimoto and Yonatan Oren and Percy Liang},
    journal = {Transactions of the Association for Computational Linguistics (TACL)},
    title = {Generating Sentences by Editing Prototypes},
    volume = {0},
    year = {2018},
  }
  

  [bib] [paper] [CodaLab]
  
• Delete, retrieve, generate: a simple approach to sentiment and style transfer. Juncen Li, Robin Jia, He He, Percy Liang. North American Association for Computational Linguistics (NAACL), 2018.

  @inproceedings{li2018style,
    author = {Juncen Li and Robin Jia and He He and Percy Liang},
    booktitle = {North American Association for Computational Linguistics (NAACL)},
    title = {Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer},
    year = {2018},
  }
  

  [bib] [paper] [CodaLab]
  
• Reinforcement learning on web interfaces using workflow-guided exploration. Evan Zheran Liu, Kelvin Guu, Panupong Pasupat, Tianlin Shi, Percy Liang. International Conference on Learning Representations (ICLR), 2018.

  @inproceedings{liu2018workflow,
    author = {Evan Zheran Liu and Kelvin Guu and Panupong Pasupat and Tianlin Shi and Percy Liang},
    booktitle = {International Conference on Learning Representations (ICLR)},
    title = {Reinforcement Learning on Web Interfaces using Workflow-Guided Exploration},
    year = {2018},
  }
  

  [bib] [paper]
  
• Certified defenses against adversarial examples. Aditi Raghunathan, Jacob Steinhardt, Percy Liang. International Conference on Learning Representations (ICLR), 2018.

  @inproceedings{raghunathan2018certified,
    author = {Aditi Raghunathan and Jacob Steinhardt and Percy Liang},
    booktitle = {International Conference on Learning Representations (ICLR)},
    title = {Certified defenses against adversarial examples},
    year = {2018},
  }
  

  [bib] [paper] [CodaLab]
  
• Active learning of points-to specifications. Osbert Bastani, Rahul Sharma, Alex Aiken, Percy Liang. Programming Language Design and Implementation (PLDI), 2018.

  @inproceedings{bastani2018active,
    author = {Osbert Bastani and Rahul Sharma and Alex Aiken and Percy Liang},
    booktitle = {Programming Language Design and Implementation (PLDI)},
    title = {Active Learning of Points-To Specifications},
    year = {2018},
  }
  

  [bib] [paper]
  
• Prediction with a short memory. Vatsal Sharan, Sham Kakade, Percy Liang, Gregory Valiant. Symposium on Theory of Computing (STOC), 2018.

  @inproceedings{sharan2018prediction,
    author = {Vatsal Sharan and Sham Kakade and Percy Liang and Gregory Valiant},
    booktitle = {Symposium on Theory of Computing (STOC)},
    title = {Prediction with a Short Memory},
    year = {2018},
  }
  

  [bib] [paper]
  
• Transforming question answering datasets into natural language inference datasets. Dorottya Demszky, Kelvin Guu, Percy Liang. arXiv preprint arXiv:1809.02922, 2018.

  @article{demszky2018transforming,
    author = {Dorottya Demszky and Kelvin Guu and Percy Liang},
    journal = {arXiv preprint arXiv:1809.02922},
    title = {Transforming Question Answering Datasets Into Natural Language Inference Datasets},
    year = {2018},
  }
  

  [bib]
  

2017

• Certified defenses for data poisoning attacks. Jacob Steinhardt, Pang Wei Koh, Percy Liang. Advances in Neural Information Processing Systems (NeurIPS), 2017.

  @inproceedings{steinhardt2017certified,
    author = {Jacob Steinhardt and Pang Wei Koh and Percy Liang},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    title = {Certified Defenses for Data Poisoning Attacks},
    year = {2017},
  }
  

  [bib] [paper] [CodaLab]
  
• Unsupervised transformation learning via convex relaxations. Tatsunori B. Hashimoto, John Duchi, Percy Liang. Advances in Neural Information Processing Systems (NeurIPS), 2017.

  @inproceedings{hashimoto2017transformation,
    author = {Tatsunori B. Hashimoto and John Duchi and Percy Liang},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    title = {Unsupervised Transformation Learning via Convex Relaxations},
    year = {2017},
  }
  

  [bib] [paper] [CodaLab]
  
• Learning overcomplete HMMs. Vatsal Sharan, Sham Kakade, Percy Liang, Gregory Valiant. Advances in Neural Information Processing Systems (NeurIPS), 2017.

  @inproceedings{sharan2017overcomplete,
    author = {Vatsal Sharan and Sham Kakade and Percy Liang and Gregory Valiant},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    title = {Learning Overcomplete {HMM}s},
    year = {2017},
  }
  

  [bib] [paper]
  
• Adversarial examples for evaluating reading comprehension systems. Robin Jia, Percy Liang. Empirical Methods in Natural Language Processing (EMNLP), 2017. Outstanding paper award.

  @inproceedings{jia2017adversarial,
    author = {Robin Jia and Percy Liang},
    booktitle = {Empirical Methods in Natural Language Processing (EMNLP)},
    title = {Adversarial Examples for Evaluating Reading Comprehension Systems},
    year = {2017},
  }
  

  [bib] [paper] [CodaLab]
  
• Macro grammars and holistic triggering for efficient semantic parsing. Yuchen Zhang, Panupong Pasupat, Percy Liang. Empirical Methods in Natural Language Processing (EMNLP), 2017.

  @inproceedings{zhang2017macro,
    author = {Yuchen Zhang and Panupong Pasupat and Percy Liang},
    booktitle = {Empirical Methods in Natural Language Processing (EMNLP)},
    title = {Macro Grammars and Holistic Triggering for Efficient Semantic Parsing},
    year = {2017},
  }
  

  [bib] [paper] [CodaLab]
  
• Importance sampling for unbiased on-demand evaluation of knowledge base population. Arun Chaganty, Ashwin Paranjape, Percy Liang, Chris Manning. Empirical Methods in Natural Language Processing (EMNLP), 2017.

  @inproceedings{chaganty2017unbiased,
    author = {Arun Chaganty and Ashwin Paranjape and Percy Liang and Chris Manning},
    booktitle = {Empirical Methods in Natural Language Processing (EMNLP)},
    title = {Importance sampling for unbiased on-demand evaluation of knowledge base population},
    year = {2017},
  }
  

  [bib] [paper]
  
• Understanding black-box predictions via influence functions. Pang Wei Koh, Percy Liang. International Conference on Machine Learning (ICML), 2017. Best paper award.

  @inproceedings{koh2017understanding,
    author = {Pang Wei Koh and Percy Liang},
    booktitle = {International Conference on Machine Learning (ICML)},
    title = {Understanding Black-box Predictions via Influence Functions},
    year = {2017},
  }
  

  [bib] [paper] [CodaLab]
  
• Convexified convolutional neural networks. Yuchen Zhang, Percy Liang, Martin J. Wainwright. International Conference on Machine Learning (ICML), 2017.

  @inproceedings{zhang2017convexified,
    author = {Yuchen Zhang and Percy Liang and Martin J. Wainwright},
    booktitle = {International Conference on Machine Learning (ICML)},
    title = {Convexified Convolutional Neural Networks},
    year = {2017},
  }
  

  [bib] [paper]
  
• Developing bug-free machine learning systems with formal mathematics. Daniel Selsam, Percy Liang, David Dill. International Conference on Machine Learning (ICML), 2017.

  @inproceedings{selsam2017bugfree,
    author = {Daniel Selsam and Percy Liang and David Dill},
    booktitle = {International Conference on Machine Learning (ICML)},
    title = {Developing Bug-Free Machine Learning Systems With Formal Mathematics},
    year = {2017},
  }
  

  [bib] [paper] [code]
  
• World of bits: an open-domain platform for web-based agents. Tianlin Shi, Andrej Karpathy, Linxi Fan, Jonathan Hernandez, Percy Liang. International Conference on Machine Learning (ICML), 2017.

  @inproceedings{shi2017wob,
    author = {Tianlin Shi and Andrej Karpathy and Linxi Fan and Jonathan Hernandez and Percy Liang},
    booktitle = {International Conference on Machine Learning (ICML)},
    title = {World of Bits: An Open-Domain Platform for Web-Based Agents},
    year = {2017},
  }
  

  [bib] [paper]
  
• A hitting time analysis of stochastic gradient Langevin dynamics. Yuchen Zhang, Percy Liang, Moses Charikar. Conference on Learning Theory (COLT), 2017. Best paper award.

  @inproceedings{zhang2017hitting,
    author = {Yuchen Zhang and Percy Liang and Moses Charikar},
    booktitle = {Conference on Learning Theory (COLT)},
    title = {A Hitting Time Analysis of Stochastic Gradient {L}angevin Dynamics},
    year = {2017},
  }
  

  [bib] [paper]
  
• Synthesizing program input grammars. Osbert Bastani, Rahul Sharma, Alex Aiken, Percy Liang. Programming Language Design and Implementation (PLDI), 2017.

  @inproceedings{bastani2017synthesizing,
    author = {Osbert Bastani and Rahul Sharma and Alex Aiken and Percy Liang},
    booktitle = {Programming Language Design and Implementation (PLDI)},
    title = {Synthesizing Program Input Grammars},
    year = {2017},
  }
  

  [bib] [paper]
  
• Naturalizing a programming language via interactive learning. Sida I. Wang, Sam Ginn, Percy Liang, Christopher D. Manning. Association for Computational Linguistics (ACL), 2017.

  @inproceedings{wang2017naturalizing,
    author = {Sida I. Wang and Sam Ginn and Percy Liang and Christopher D. Manning},
    booktitle = {Association for Computational Linguistics (ACL)},
    title = {Naturalizing a Programming Language via Interactive Learning},
    year = {2017},
  }
  

  [bib] [paper] [project] [CodaLab]
  
• Learning symmetric collaborative dialogue agents with dynamic knowledge graph embeddings. He He, Anusha Balakrishnan, Mihail Eric, Percy Liang. Association for Computational Linguistics (ACL), 2017.

  @inproceedings{he2017symmetric,
    author = {He He and Anusha Balakrishnan and Mihail Eric and Percy Liang},
    booktitle = {Association for Computational Linguistics (ACL)},
    pages = {1766--1776},
    title = {Learning Symmetric Collaborative Dialogue Agents with Dynamic Knowledge Graph Embeddings},
    year = {2017},
  }
  

  [bib] [paper] [CodaLab]
  
• From language to programs: bridging reinforcement learning and maximum marginal likelihood. Kelvin Guu, Panupong Pasupat, Evan Zheran Liu, Percy Liang. Association for Computational Linguistics (ACL), 2017.

  @inproceedings{guu2017bridging,
    author = {Kelvin Guu and Panupong Pasupat and Evan Zheran Liu and Percy Liang},
    booktitle = {Association for Computational Linguistics (ACL)},
    title = {From Language to Programs: Bridging Reinforcement Learning and Maximum Marginal Likelihood},
    year = {2017},
  }
  

  [bib] [paper] [CodaLab]
  

2016

• Unsupervised risk estimation using only conditional independence structure. Jacob Steinhardt, Percy Liang. Advances in Neural Information Processing Systems (NeurIPS), 2016.

  @inproceedings{steinhardt2016risk,
    author = {Jacob Steinhardt and Percy Liang},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    title = {Unsupervised Risk Estimation Using Only Conditional Independence Structure},
    year = {2016},
  }
  

  [bib] [paper]
  
• SQuAD: 100,000+ questions for machine comprehension of text. Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, Percy Liang. Empirical Methods in Natural Language Processing (EMNLP), 2016. Best resource paper award.

  @inproceedings{rajpurkar2016squad,
    author = {Pranav Rajpurkar and Jian Zhang and Konstantin Lopyrev and Percy Liang},
    booktitle = {Empirical Methods in Natural Language Processing (EMNLP)},
    title = {{SQuAD}: 100,000+ Questions for Machine Comprehension of Text},
    year = {2016},
  }
  

  [bib] [paper] [CodaLab]
  
• Learning language games through interaction. Sida I. Wang, Percy Liang, Chris Manning. Association for Computational Linguistics (ACL), 2016. Outstanding paper award.

  @inproceedings{wang2016games,
    author = {Sida I. Wang and Percy Liang and Chris Manning},
    booktitle = {Association for Computational Linguistics (ACL)},
    title = {Learning Language Games through Interaction},
    year = {2016},
  }
  

  [bib] [paper] [CodaLab]
  
• Data recombination for neural semantic parsing. Robin Jia, Percy Liang. Association for Computational Linguistics (ACL), 2016.

  @inproceedings{jia2016recombination,
    author = {Robin Jia and Percy Liang},
    booktitle = {Association for Computational Linguistics (ACL)},
    title = {Data Recombination for Neural Semantic Parsing},
    year = {2016},
  }
  

  [bib] [paper] [CodaLab]
  
• Simpler context-dependent logical forms via model projections. Reginald Long, Panupong Pasupat, Percy Liang. Association for Computational Linguistics (ACL), 2016.

  @inproceedings{long2016projections,
    author = {Reginald Long and Panupong Pasupat and Percy Liang},
    booktitle = {Association for Computational Linguistics (ACL)},
    title = {Simpler Context-Dependent Logical Forms via Model Projections},
    year = {2016},
  }
  

  [bib] [paper] [CodaLab]
  
• Inferring logical forms from denotations. Panupong Pasupat, Percy Liang. Association for Computational Linguistics (ACL), 2016.

  @inproceedings{pasupat2016inferring,
    author = {Panupong Pasupat and Percy Liang},
    booktitle = {Association for Computational Linguistics (ACL)},
    title = {Inferring Logical Forms From Denotations},
    year = {2016},
  }
  

  [bib] [paper] [CodaLab]
  
• Unanimous prediction for 100% precision with application to learning semantic mappings. Fereshte Khani, Martin Rinard, Percy Liang. Association for Computational Linguistics (ACL), 2016.

  @inproceedings{khani2016unanimity,
    author = {Fereshte Khani and Martin Rinard and Percy Liang},
    booktitle = {Association for Computational Linguistics (ACL)},
    title = {Unanimous Prediction for 100% Precision with Application to Learning Semantic Mappings},
    year = {2016},
  }
  

  [bib] [paper] [CodaLab]
  
• How much is 131 million dollars? Putting numbers in perspective with compositional descriptions. Arun Tejasvi Chaganty, Percy Liang. Association for Computational Linguistics (ACL), 2016.

  @inproceedings{chaganty2016perspectives,
    author = {Arun Tejasvi Chaganty and Percy Liang},
    booktitle = {Association for Computational Linguistics (ACL)},
    title = {How Much is 131 Million Dollars? {P}utting Numbers in Perspective with Compositional Descriptions},
    year = {2016},
  }
  

  [bib] [paper] [CodaLab]
  
• Estimation from indirect supervision with linear moments. Aditi Raghunathan, Roy Frostig, John Duchi, Percy Liang. International Conference on Machine Learning (ICML), 2016.

  @inproceedings{raghunathan2016linear,
    author = {Aditi Raghunathan and Roy Frostig and John Duchi and Percy Liang},
    booktitle = {International Conference on Machine Learning (ICML)},
    title = {Estimation from Indirect Supervision with Linear Moments},
    year = {2016},
  }
  

  [bib] [paper] [CodaLab]
  
• Data augmentation via Lévy processes. Stefan Wager, Will Fithian, Percy Liang. Perturbations, Optimization and Statistics, 2016.

  @incollection{wager2016levy,
    author = {Stefan Wager and Will Fithian and Percy Liang},
    booktitle = {Perturbations, Optimization and Statistics},
    title = {Data Augmentation via {L}évy Processes},
    year = {2016},
  }
  

  [bib] [paper] [code]
  
• Learning executable semantic parsers for natural language understanding. Percy Liang. Communications of the ACM, 2016.

  @article{liang2016executable,
    author = {Percy Liang},
    journal = {Communications of the ACM},
    title = {Learning Executable Semantic Parsers for Natural Language Understanding},
    volume = {59},
    year = {2016},
  }
  

  [bib] [paper]
  

2015

• Building a semantic parser overnight. Yushi Wang, Jonathan Berant, Percy Liang. Association for Computational Linguistics (ACL), 2015.

  @inproceedings{wang2015overnight,
    author = {Yushi Wang and Jonathan Berant and Percy Liang},
    booktitle = {Association for Computational Linguistics (ACL)},
    title = {Building a Semantic Parser Overnight},
    year = {2015},
  }
  

  [bib] [paper] [project] [CodaLab]
  
• Imitation learning of agenda-based semantic parsers. Jonathan Berant, Percy Liang. Transactions of the Association for Computational Linguistics (TACL), 2015.

  @article{berant2015agenda,
    author = {Jonathan Berant and Percy Liang},
    journal = {Transactions of the Association for Computational Linguistics (TACL)},
    pages = {545--558},
    title = {Imitation Learning of Agenda-Based Semantic Parsers},
    volume = {3},
    year = {2015},
  }
  

  [bib] [paper] [project] [CodaLab]
  
• Learning with relaxed supervision. Jacob Steinhardt, Percy Liang. Advances in Neural Information Processing Systems (NeurIPS), 2015.

  @inproceedings{steinhardt2015relaxed,
    author = {Jacob Steinhardt and Percy Liang},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    title = {Learning with Relaxed Supervision},
    year = {2015},
  }
  

  [bib] [paper] [CodaLab]
  
• Estimating mixture models via mixture of polynomials. Sida I. Wang, Arun Chaganty, Percy Liang. Advances in Neural Information Processing Systems (NeurIPS), 2015.

  @inproceedings{wang2015polynomial,
    author = {Sida I. Wang and Arun Chaganty and Percy Liang},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    title = {Estimating Mixture Models via Mixture of Polynomials},
    year = {2015},
  }
  

  [bib] [paper] [CodaLab]
  
• On-the-Job learning with Bayesian decision theory. Keenon Werling, Arun Chaganty, Percy Liang, Chris Manning. Advances in Neural Information Processing Systems (NeurIPS), 2015.

  @inproceedings{werling2015onthejob,
    author = {Keenon Werling and Arun Chaganty and Percy Liang and Chris Manning},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    title = {On-the-Job Learning with {B}ayesian Decision Theory},
    year = {2015},
  }
  

  [bib] [paper] [CodaLab]
  
• Calibrated structured prediction. Volodymyr Kuleshov, Percy Liang. Advances in Neural Information Processing Systems (NeurIPS), 2015.

  @inproceedings{kuleshov2015calibrated,
    author = {Volodymyr Kuleshov and Percy Liang},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    title = {Calibrated Structured Prediction},
    year = {2015},
  }
  

  [bib] [paper] [CodaLab]
  
• Traversing knowledge graphs in vector space. Kelvin Guu, John Miller, Percy Liang. Empirical Methods in Natural Language Processing (EMNLP), 2015. Best paper honorable mention.

  @inproceedings{guu2015traversing,
    author = {Kelvin Guu and John Miller and Percy Liang},
    booktitle = {Empirical Methods in Natural Language Processing (EMNLP)},
    title = {Traversing Knowledge Graphs in Vector Space},
    year = {2015},
  }
  

  [bib] [paper] [CodaLab]
  
• Compositional semantic parsing on semi-structured tables. Panupong Pasupat, Percy Liang. Association for Computational Linguistics (ACL), 2015.

  @inproceedings{pasupat2015compositional,
    author = {Panupong Pasupat and Percy Liang},
    booktitle = {Association for Computational Linguistics (ACL)},
    title = {Compositional Semantic Parsing on Semi-Structured Tables},
    year = {2015},
  }
  

  [bib] [paper] [CodaLab]
  
• Environment-Driven lexicon induction for high-level instructions. Dipendra K. Misra, Kejia Tao, Percy Liang, Ashutosh Saxena. Association for Computational Linguistics (ACL), 2015.

  @inproceedings{misra2015environment,
    author = {Dipendra K. Misra and Kejia Tao and Percy Liang and Ashutosh Saxena},
    booktitle = {Association for Computational Linguistics (ACL)},
    title = {Environment-Driven Lexicon Induction for High-Level Instructions},
    year = {2015},
  }
  

  [bib] [paper] [CodaLab]
  
• Reified context models. Jacob Steinhardt, Percy Liang. International Conference on Machine Learning (ICML), 2015.

  @inproceedings{steinhardt2015rcm,
    author = {Jacob Steinhardt and Percy Liang},
    booktitle = {International Conference on Machine Learning (ICML)},
    title = {Reified Context Models},
    year = {2015},
  }
  

  [bib] [paper] [CodaLab]
  
• Learning fast-mixing models for structured prediction. Jacob Steinhardt, Percy Liang. International Conference on Machine Learning (ICML), 2015.

  @inproceedings{steinhardt2015fast,
    author = {Jacob Steinhardt and Percy Liang},
    booktitle = {International Conference on Machine Learning (ICML)},
    pages = {1063--1072},
    title = {Learning Fast-Mixing Models for Structured Prediction},
    year = {2015},
  }
  

  [bib] [paper] [CodaLab]
  
• Learning where to sample in structured prediction. Tianlin Shi, Jacob Steinhardt, Percy Liang. Artificial Intelligence and Statistics (AISTATS), 2015.

  @inproceedings{shi2015sample,
    author = {Tianlin Shi and Jacob Steinhardt and Percy Liang},
    booktitle = {Artificial Intelligence and Statistics (AISTATS)},
    pages = {875--884},
    title = {Learning Where To Sample in Structured Prediction},
    year = {2015},
  }
  

  [bib] [paper] [CodaLab]
  
• Tensor factorization via matrix factorization. Volodymyr Kuleshov, Arun Chaganty, Percy Liang. Artificial Intelligence and Statistics (AISTATS), 2015.

  @inproceedings{kuleshov2015tensor,
    author = {Volodymyr Kuleshov and Arun Chaganty and Percy Liang},
    booktitle = {Artificial Intelligence and Statistics (AISTATS)},
    title = {Tensor factorization via matrix factorization},
    year = {2015},
  }
  

  [bib] [paper] [CodaLab]
  
• Bringing machine learning and compositional semantics together. Percy Liang, Christopher Potts. Annual Reviews of Linguistics, 2015.

  @article{liang2015semantics,
    author = {Percy Liang and Christopher Potts},
    journal = {Annual Reviews of Linguistics},
    number = {1},
    pages = {355--376},
    title = {Bringing machine learning and compositional semantics together},
    volume = {1},
    year = {2015},
  }
  

  [bib] [paper]
  

2014

• The statistics of streaming sparse regression. Jacob Steinhardt, Stefan Wager, Percy Liang. arXiv preprint arXiv:1412.4182, 2014.

  @article{steinhardt2014sparse,
    author = {Jacob Steinhardt and Stefan Wager and Percy Liang},
    journal = {arXiv preprint arXiv:1412.4182},
    title = {The Statistics of Streaming Sparse Regression},
    year = {2014},
  }
  

  [bib] [paper]
  
• Linking people with "their" names using coreference resolution. Vignesh Ramanathan, Armand Joulin, Percy Liang, Li Fei-Fei. European Conference on Computer Vision (ECCV), 2014.

  @inproceedings{ramanathan2014linking,
    author = {Vignesh Ramanathan and Armand Joulin and Percy Liang and Li Fei-Fei},
    booktitle = {European Conference on Computer Vision (ECCV)},
    title = {Linking people with "their" names using coreference resolution},
    year = {2014},
  }
  

  [bib] [paper] [supplemental material]
  
• Talking to computers in natural language. Percy Liang. XRDS: Crossroads, The ACM Magazine for Students, 2014.

  @article{liang2014talking,
    author = {Percy Liang},
    journal = {XRDS: Crossroads, The ACM Magazine for Students},
    number = {1},
    pages = {18--21},
    title = {Talking to computers in natural language},
    volume = {21},
    year = {2014},
  }
  

  [bib] [paper]
  
• Semantic parsing via paraphrasing. Jonathan Berant, Percy Liang. Association for Computational Linguistics (ACL), 2014. Best long paper honorable mention.

  @inproceedings{berant2014paraphrasing,
    author = {Jonathan Berant and Percy Liang},
    booktitle = {Association for Computational Linguistics (ACL)},
    title = {Semantic Parsing via Paraphrasing},
    year = {2014},
  }
  

  [bib] [paper] [project]
  
• Zero-shot entity extraction from web pages. Panupong Pasupat, Percy Liang. Association for Computational Linguistics (ACL), 2014.

  @inproceedings{pasupat2014extraction,
    author = {Panupong Pasupat and Percy Liang},
    booktitle = {Association for Computational Linguistics (ACL)},
    title = {Zero-shot Entity Extraction from Web Pages},
    year = {2014},
  }
  

  [bib] [paper] [slides] [project]
  
• Estimating latent-variable graphical models using moments and likelihoods. Arun Chaganty, Percy Liang. International Conference on Machine Learning (ICML), 2014.

  @inproceedings{chaganty2014graphical,
    author = {Arun Chaganty and Percy Liang},
    booktitle = {International Conference on Machine Learning (ICML)},
    title = {Estimating Latent-Variable Graphical Models using Moments and Likelihoods},
    year = {2014},
  }
  

  [bib] [paper] [slides]
  
• Adaptivity and optimism: an improved exponentiated gradient algorithm. Jacob Steinhardt, Percy Liang. International Conference on Machine Learning (ICML), 2014.

  @inproceedings{steinhardt2014eg,
    author = {Jacob Steinhardt and Percy Liang},
    booktitle = {International Conference on Machine Learning (ICML)},
    title = {Adaptivity and Optimism: An Improved Exponentiated Gradient Algorithm},
    year = {2014},
  }
  

  [bib] [paper]
  
• Filtering with abstract particles. Jacob Steinhardt, Percy Liang. International Conference on Machine Learning (ICML), 2014.

  @inproceedings{steinhardt2014filtering,
    author = {Jacob Steinhardt and Percy Liang},
    booktitle = {International Conference on Machine Learning (ICML)},
    pages = {727--735},
    title = {Filtering with Abstract Particles},
    year = {2014},
  }
  

  [bib] [paper] [supplemental material]
  
• Altitude training: strong bounds for single-layer dropout. Stefan Wager, Will Fithian, Sida I. Wang, Percy Liang. Advances in Neural Information Processing Systems (NeurIPS), 2014.

  @inproceedings{wager2014altitude,
    author = {Stefan Wager and Will Fithian and Sida I. Wang and Percy Liang},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    title = {Altitude Training: Strong Bounds for Single-Layer Dropout},
    year = {2014},
  }
  

  [bib] [paper]
  
• Simple MAP inference via low-rank relaxations. Roy Frostig, Sida I. Wang, Percy Liang, Chris Manning. Advances in Neural Information Processing Systems (NeurIPS), 2014.

  @inproceedings{frostig2014lowrank,
    author = {Roy Frostig and Sida I. Wang and Percy Liang and Chris Manning},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    title = {Simple {MAP} inference via low-rank relaxations},
    year = {2014},
  }
  

  [bib] [paper] [CodaLab]
  
• Relaxations for inference in restricted Boltzmann machines. Sida I. Wang, Roy Frostig, Percy Liang, Chris Manning. International Conference on Learning Representations Workshop (ICLR), 2014.

  @inproceedings{wang2014iqp,
    author = {Sida I. Wang and Roy Frostig and Percy Liang and Chris Manning},
    booktitle = {International Conference on Learning Representations Workshop (ICLR)},
    title = {Relaxations for inference in restricted {B}oltzmann machines},
    year = {2014},
  }
  

  [bib] [paper]
  

2013

• Lambda dependency-based compositional semantics. Percy Liang. arXiv preprint arXiv:1309.4408, 2013.

  @article{liang2013lambdadcs,
    author = {Percy Liang},
    journal = {arXiv preprint arXiv:1309.4408},
    title = {Lambda Dependency-Based Compositional Semantics},
    year = {2013},
  }
  

  [bib] [paper]
  
• Semantic parsing on Freebase from question-answer pairs. Jonathan Berant, Andrew Chou, Roy Frostig, Percy Liang. Empirical Methods in Natural Language Processing (EMNLP), 2013.

  @inproceedings{berant2013freebase,
    author = {Jonathan Berant and Andrew Chou and Roy Frostig and Percy Liang},
    booktitle = {Empirical Methods in Natural Language Processing (EMNLP)},
    title = {Semantic Parsing on {F}reebase from Question-Answer Pairs},
    year = {2013},
  }
  

  [bib] [paper] [supplemental material] [slides] [project]
  
• Feature noising for log-linear structured prediction. Sida I. Wang, Mengqiu Wang, Stefan Wager, Percy Liang, Chris Manning. Empirical Methods in Natural Language Processing (EMNLP), 2013.

  @inproceedings{wang2013noising,
    author = {Sida I. Wang and Mengqiu Wang and Stefan Wager and Percy Liang and Chris Manning},
    booktitle = {Empirical Methods in Natural Language Processing (EMNLP)},
    title = {Feature Noising for Log-linear Structured Prediction},
    year = {2013},
  }
  

  [bib] [paper]
  
• Dropout training as adaptive regularization. Stefan Wager, Sida I. Wang, Percy Liang. Advances in Neural Information Processing Systems (NeurIPS), 2013.

  @inproceedings{wager2013dropout,
    author = {Stefan Wager and Sida I. Wang and Percy Liang},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    title = {Dropout Training as Adaptive Regularization},
    year = {2013},
  }
  

  [bib] [paper] [poster]
  
• Spectral experts for estimating mixtures of linear regressions. Arun Chaganty, Percy Liang. International Conference on Machine Learning (ICML), 2013.

  @inproceedings{chaganty13regression,
    author = {Arun Chaganty and Percy Liang},
    booktitle = {International Conference on Machine Learning (ICML)},
    title = {Spectral Experts for Estimating Mixtures of Linear Regressions},
    year = {2013},
  }
  

  [bib] [paper]
  
• Video event understanding using natural language descriptions. Vignesh Ramanathan, Percy Liang, Li Fei-Fei. International Conference on Computer Vision (ICCV), 2013.

  @inproceedings{ramanathan2013event,
    author = {Vignesh Ramanathan and Percy Liang and Li Fei-Fei},
    booktitle = {International Conference on Computer Vision (ICCV)},
    title = {Video Event Understanding using Natural Language Descriptions},
    year = {2013},
  }
  

  [bib] [paper]
  
• A data driven approach for algebraic loop invariants. Rahul Sharma, Saurabh Gupta, Bharath Hariharan, Alex Aiken, Percy Liang, Aditya V. Nori. European Symposium on Programming (ESOP), 2013.

  @inproceedings{sharma13algebraic,
    author = {Rahul Sharma and Saurabh Gupta and Bharath Hariharan and Alex Aiken and Percy Liang and Aditya V. Nori},
    booktitle = {European Symposium on Programming (ESOP)},
    title = {A Data Driven Approach for Algebraic Loop Invariants},
    year = {2013},
  }
  

  [bib] [paper]
  

2012

• Identifiability and unmixing of latent parse trees. Daniel Hsu, Sham M. Kakade, Percy Liang. Advances in Neural Information Processing Systems (NeurIPS), 2012.

  This paper explores unsupervised learning of parsing models along two directions. First, which models are identifiable from infinite data? We use a general technique for numerically checking identifiability based on the rank of a Jacobian matrix, and apply it to several standard constituency and dependency parsing models. Second, for identifiable models, how do we estimate the parameters efficiently? EM suffers from local optima, while recent work using spectral methods cannot be directly applied since the topology of the parse tree varies across sentences. We develop a strategy, unmixing, which deals with this additional complexity for restricted classes of parsing models.

  @inproceedings{hsu12identifiability,
    author = {Daniel Hsu and Sham M. Kakade and Percy Liang},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    title = {Identifiability and Unmixing of Latent Parse Trees},
    year = {2012},
  }
  

  [abstract] [bib] [paper] [techreport] [poster]
  

2011

• Learning dependency-based compositional semantics. Percy Liang, Michael I. Jordan, Dan Klein. Association for Computational Linguistics (ACL), 2011.

  Compositional question answering begins by mapping questions to logical forms, but training a semantic parser to perform this mapping typically requires the costly annotation of the target logical forms. In this paper, we learn to map questions to answers via latent logical forms, which are induced automatically from question-answer pairs. In tackling this challenging learning problem, we introduce a new semantic representation which highlights a parallel between dependency syntax and efficient evaluation of logical forms. On two standard semantic parsing benchmarks (GEO and JOBS), our system obtains the highest published accuracies, despite using less supervision than existing systems.

  Task: learn to map questions to answers via latent logical forms.
  Contribution: new tree-based semantic representation.
  Result: surpass state-of-the-art on semantic parsing with less supervision.

  @inproceedings{liang11dcs,
    author = {Percy Liang and Michael I. Jordan and Dan Klein},
    booktitle = {Association for Computational Linguistics (ACL)},
    pages = {590--599},
    title = {Learning Dependency-Based Compositional Semantics},
    year = {2011},
  }
  

  [abstract] [brief] [bib] [paper] [thesis] [journal] [slides] [code]
  
• Scaling up abstraction refinement via pruning. Percy Liang, Mayur Naik. Programming Language Design and Implementation (PLDI), 2011.

  Many static analyses do not scale as they are made more precise. For example, increasing the amount of context sensitivity in a k-limited pointer analysis causes the number of contexts to grow exponentially with k. Iterative refinement techniques can mitigate this growth by starting with a coarse abstraction and only refining parts of the abstraction that are deemed relevant with respect to a given client.
  In this paper, we introduce a new technique called pruning that uses client feedback in a different way. The basic idea is to use coarse abstractions to prune away parts of the program analysis deemed irrelevant for proving a client query, and then using finer abstractions on the sliced program analysis. For a k-limited pointer analysis, this approach amounts to adaptively refining and pruning a set of prefix patterns representing the contexts relevant for the client. By pruning, we are able to scale up to much more expensive abstractions than before. We also prove that the pruned analysis is both sound and complete, that is, it yields the same results as an analysis that uses a more expensive abstraction directly without pruning.

  Idea: run cheap analysis, use client feedback to prune away irrelvant parts of program analysis (think program slicing); then run expensive analysis.
  Theoretical result: pruning is sound and complete.
  Empirical result: we can use much richer $k$-object-sensitivity abstractions.

  @inproceedings{liang11pruning,
    author = {Percy Liang and Mayur Naik},
    booktitle = {Programming Language Design and Implementation (PLDI)},
    title = {Scaling up Abstraction Refinement via Pruning},
    year = {2011},
  }
  

  [abstract] [brief] [bib] [paper] [slides]
  
• Learning minimal abstractions. Percy Liang, Omer Tripp, Mayur Naik. Principles of Programming Languages (POPL), 2011.

  Static analyses are generally parametrized by an abstraction which is chosen from a family of abstractions. We are interested in flexible families of abstractions with many parameters, as these families can allow one to increase precision in ways tailored to the client without sacrificing scalability. For example, we consider k-limited points-to analyses where each call site and allocation site in a program can have a different k value. We then ask a natural question in this paper: What is the minimal (coarsest) abstraction in a given family which is able to prove a set of queries? In addressing this question, we make the following two contributions: (i) We introduce two machine learning algorithms for efficiently finding a minimal abstraction; and (ii) for a static race detector backed by a k-limited points-to analysis, we show empirically that minimal abstractions are actually quite coarse: It suffices to provide context/object sensitivity to a very small fraction (0.4--2.3%) of the sites to yield equally precise results as providing context/object sensitivity uniformly to all sites.

  Question: how small is the smallest abstraction needed to prove a query?
  Empirical answer: very small (less than 2.5% sites need to be treated context-sensitively for k-limited analyses for race detection).
  Found this answer using a new machine learning algorithm that exploits this sparsity.

  @inproceedings{liang11minimal,
    author = {Percy Liang and Omer Tripp and Mayur Naik},
    booktitle = {Principles of Programming Languages (POPL)},
    title = {Learning Minimal Abstractions},
    year = {2011},
  }
  

  [abstract] [brief] [bib] [paper] [slides]
  

2010

• A game-theoretic approach to generating spatial descriptions. Dave Golland, Percy Liang, Dan Klein. Empirical Methods in Natural Language Processing (EMNLP), 2010.

  @inproceedings{golland2010pragmatics,
    author = {Dave Golland and Percy Liang and Dan Klein},
    booktitle = {Empirical Methods in Natural Language Processing (EMNLP)},
    pages = {410--419},
    title = {A Game-theoretic Approach to Generating Spatial Descriptions},
    year = {2010},
  }
  

  [bib] [paper] [slides]
  
• A simple domain-independent probabilistic approach to generation. Gabor Angeli, Percy Liang, Dan Klein. Empirical Methods in Natural Language Processing (EMNLP), 2010.

  We present a simple, robust generation system which performs content selection and surface realization in a unified, domain-independent framework. In our approach, we break up the end-to-end generation process into a sequence of local decisions, arranged hierarchically and each trained discriminatively. We deployed our system in three different domains---Robocup sportscasting, technical weather forecasts, and common weather forecasts, obtaining results comparable to state-of-the-art domain-specific systems both in terms of BLEU scores and human evaluation.

  Model natural language generation as a sequence of local decisions, each backed by a log-linear model.
  Advantage: can use arbitrary expressive features, works across multiple domains.

  @inproceedings{angeli10generation,
    author = {Gabor Angeli and Percy Liang and Dan Klein},
    booktitle = {Empirical Methods in Natural Language Processing (EMNLP)},
    title = {A Simple Domain-Independent Probabilistic Approach to Generation},
    year = {2010},
  }
  

  [abstract] [brief] [bib] [paper] [slides]
  
• A dynamic evaluation of static heap abstractions. Percy Liang, Omer Tripp, Mayur Naik, Mooly Sagiv. Object-Oriented Programming, Systems, Languages, and Applications (OOPSLA), 2010.

  The quality of a static analysis of heap-manipulating programs is largely determined by its heap abstraction. Object allocation sites are a commonly-used abstraction, but are too coarse for some clients. The goal of this paper is to investigate how various refinements of allocation sites can improve precision. In particular, we consider abstractions that use call stack, object recency, and heap connectivity information. We measure the precision of these abstractions dynamically for four different clients motivated by concurrency and on nine Java programs chosen from the DaCapo benchmark suite. Our dynamic results shed new light on aspects of heap abstractions that matter for precision, which allows us to more effectively navigate the large space of possible heap abstractions.

  Question: what aspects of a heap abstraction matter?
  Methodology: run program (9 DaCapo benchmarks) dynamically, compute static heap abstractions (3 dimensions of refinement: context sensitivity, object recency, and shape analysis), answer client queries (4 clients based on concurrency).

  @inproceedings{liang10abstraction,
    author = {Percy Liang and Omer Tripp and Mayur Naik and Mooly Sagiv},
    booktitle = {Object-Oriented Programming, Systems, Languages, and Applications (OOPSLA)},
    title = {A Dynamic Evaluation of Static Heap Abstractions},
    year = {2010},
  }
  

  [abstract] [brief] [bib] [paper] [slides]
  
• Learning programs: a hierarchical Bayesian approach. Percy Liang, Michael I. Jordan, Dan Klein. International Conference on Machine Learning (ICML), 2010.

  We are interested in learning programs for multiple related tasks given only a few training examples per task. Since the program for a single task is underdetermined by its data, we introduce a nonparametric hierarchical Bayesian prior over programs which shares statistical strength across multiple tasks. The key challenge is to parametrize this multi-task sharing. For this, we introduce a new representation of programs based on combinatory logic and provide an MCMC algorithm that can perform safe program transformations on this representation to reveal shared inter-program substructures.

  Programs are trees, subprograms are subtrees, which can be shared across tasks. Combinators refactor programs to expose the appropriate subprograms.

  @inproceedings{liang10programs,
    author = {Percy Liang and Michael I. Jordan and Dan Klein},
    booktitle = {International Conference on Machine Learning (ICML)},
    pages = {639--646},
    title = {Learning Programs: A Hierarchical {B}ayesian Approach},
    year = {2010},
  }
  

  [abstract] [brief] [bib] [paper] [slides] [code]
  
• On the interaction between norm and dimensionality: multiple regimes in learning. Percy Liang, Nati Srebro. International Conference on Machine Learning (ICML), 2010.

  A learning problem might have several measures of complexity (e.g., norm and dimensionality) that affect the generalization error. What is the interaction between these complexities? Dimension-free learning theory bounds and parametric asymptotic analyses each provide a partial picture of the full learning curve. In this paper, we use high-dimensional asymptotics on two classical problems---mean estimation and linear regression---to explore the learning curve more completely. We show that these curves exhibit multiple regimes, where in each regime, the excess risk is controlled by a subset of the problem complexities.

  Goal: understand excess risk as a function of sample size and problem complexity. On simple examples, show that asymptotic risk has multiple regimes, each controlled by different complexities.

  @inproceedings{liang10regimes,
    author = {Percy Liang and Nati Srebro},
    booktitle = {International Conference on Machine Learning (ICML)},
    title = {On the Interaction between Norm and Dimensionality: Multiple Regimes in Learning},
    year = {2010},
  }
  

  [abstract] [brief] [bib] [paper] [slides]
  
• Type-Based MCMC. Percy Liang, Michael I. Jordan, Dan Klein. North American Association for Computational Linguistics (NAACL), 2010.

  Most existing algorithms for learning latent-variable models---such as EM and existing Gibbs samplers---are token-based, meaning that they update the variables associated with one sentence at a time. The incremental nature of these methods makes them susceptible to local optima/slow mixing. In this paper, we introduce a type-based sampler, which updates a block of variables, identified by a type, which spans multiple sentences. We show improvements on part-of-speech induction, word segmentation, and learning tree-substitution grammars.

  NLP perspective: goal is to avoid local optima by processing all tokens associated with a type at once instead of one token or sentence at a time.
  Sampling perspective: new type of block sampling that exploits exchangeability.

  @inproceedings{liang10type,
    author = {Percy Liang and Michael I. Jordan and Dan Klein},
    booktitle = {North American Association for Computational Linguistics (NAACL)},
    title = {Type-Based {MCMC}},
    year = {2010},
  }
  

  [abstract] [brief] [bib] [paper] [slides] [code]
  

2009

• Asymptotically optimal regularization in smooth parametric models. Percy Liang, Francis Bach, Guillaume Bouchard, Michael I. Jordan. Advances in Neural Information Processing Systems (NeurIPS), 2009.

  Many types of regularization schemes have been employed in statistical learning, each one motivated by some assumption about the problem domain. In this paper, we present a unified asymptotic analysis of smooth regularizers, which allows us to see how the validity of these assumptions impacts the success of a particular regularizer. In addition, our analysis motivates an algorithm for optimizing regularization parameters, which in turn can be analyzed within our framework. We apply our analysis to several examples, including hybrid generative-discriminative learning and multi-task learning.

  Setting: estimator defined by minimizing loss plus regularization.
  Question: what is the best regularizer to use?
  This is hard to optimize, so use a Taylor expansion instead, yielding a interpretable closed form solution.

  @inproceedings{liang09regularization,
    author = {Percy Liang and Francis Bach and Guillaume Bouchard and Michael I. Jordan},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    title = {Asymptotically Optimal Regularization in Smooth Parametric Models},
    year = {2009},
  }
  

  [abstract] [brief] [bib] [paper] [techreport] [poster]
  
• Probabilistic grammars and hierarchical Dirichlet processes. Percy Liang, Michael I. Jordan, Dan Klein. The Oxford Handbook of Applied Bayesian Analysis, 2009.

  Probabilistic context-free grammars (PCFGs) have played an important role in the modeling of syntax in natural language processing and other applications, but choosing the proper model complexity is often difficult. We present a nonparametric Bayesian generalization of the PCFG based on the hierarchical Dirichlet process (HDP). In our HDP-PCFG model, the effective complexity of the grammar can grow with increasing data. We describe an efficient variational inference algorithm for our model and present experiments on both a synthetic grammar induction task and a large-scale natural language parsing task.

  Details of the EMNLP 2007 paper + general background, empirical intuitions, and derivations for structured mean-field + a small grammar induction experiment.

  @incollection{liang09hdppcfg,
    author = {Percy Liang and Michael I. Jordan and Dan Klein},
    booktitle = {The Oxford Handbook of Applied Bayesian Analysis},
    title = {Probabilistic grammars and hierarchical {D}irichlet processes},
    year = {2009},
  }
  

  [abstract] [brief] [bib] [paper]
  
• Learning semantic correspondences with less supervision. Percy Liang, Michael I. Jordan, Dan Klein. Association for Computational Linguistics and International Joint Conference on Natural Language Processing (ACL-IJCNLP), 2009.

  A central problem in grounded language acquisition is learning the correspondences between a rich world state and a stream of text which references that world state. To deal with the high degree of ambiguity present in this setting, we present a generative model that simultaneously segments the text into utterances and maps each utterance to a meaning representation grounded in the world state. We show that our model generalizes across three domains of increasing difficulty---Robocup sportscasting, weather forecasts (a new domain), and NFL recaps.

  Stuff happens in the world. A text talks about it. Our goal: learn the correspondence between the two.
  Approach: probabilistic model capturing identification of entities/events in the world, segmentation of the text, and alignment between the two.

  @inproceedings{liang09semantics,
    author = {Percy Liang and Michael I. Jordan and Dan Klein},
    booktitle = {Association for Computational Linguistics and International Joint Conference on Natural Language Processing (ACL-IJCNLP)},
    pages = {91--99},
    title = {Learning Semantic Correspondences with Less Supervision},
    year = {2009},
  }
  

  [abstract] [brief] [bib] [paper] [slides] [code]
  
• Learning from measurements in exponential families. Percy Liang, Michael I. Jordan, Dan Klein. International Conference on Machine Learning (ICML), 2009.

  Given a model family and a set of unlabeled examples, one could either label specific examples or state general constraints---both provide information about the desired model. In general, what is the most cost-effective way to learn? To address this question, we introduce measurements, a general class of mechanisms for providing information about a target model. We present a Bayesian decision-theoretic framework, which allows us to both integrate diverse measurements and choose new measurements to make. We use a variational inference algorithm, which exploits exponential family duality. The merits of our approach are demonstrated on two sequence labeling tasks.

  Goal: learning with minimum human effort.
  Things human can do: label data, provide constraints---in general, make measurements.
  Use Bayesian decision theory to choose optimal measurements.

  @inproceedings{liang09measurements,
    author = {Percy Liang and Michael I. Jordan and Dan Klein},
    booktitle = {International Conference on Machine Learning (ICML)},
    title = {Learning from Measurements in Exponential Families},
    year = {2009},
  }
  

  [abstract] [brief] [bib] [paper] [slides]
  
• Online EM for unsupervised models. Percy Liang, Dan Klein. North American Association for Computational Linguistics (NAACL), 2009.

  The (batch) EM algorithm plays an important role in unsupervised induction, but it sometimes suffers from slow convergence. In this paper, we show that online variants (1) provide significant speedups and (2) can even find better solutions than those found by batch EM. We support these findings on four unsupervised tasks: part-of-speech tagging, document classification, word segmentation, and word alignment.

  What you'd expect: online is faster than batch.
  What you might not expect: online gets better accuarcy than batch.

  @inproceedings{liang09online,
    author = {Percy Liang and Dan Klein},
    booktitle = {North American Association for Computational Linguistics (NAACL)},
    pages = {611--619},
    title = {Online {EM} for Unsupervised Models},
    year = {2009},
  }
  

  [abstract] [brief] [bib] [paper] [slides] [code]
  

2008

• An asymptotic analysis of generative, discriminative, and pseudolikelihood estimators. Percy Liang, Michael I. Jordan. International Conference on Machine Learning (ICML), 2008. Best student paper award.

  Statistical and computational concerns have motivated parameter estimators based on various forms of likelihood, e.g., joint, conditional, and pseudolikelihood. In this paper, we present a unified framework for studying these estimators, which allows us to compare their relative (statistical) efficiencies. Our asymptotic analysis suggests that modeling more of the data tends to reduce variance, but at the cost of being more sensitive to model misspecification. We present experiments validating our analysis.

  Derive general expression for the asymptotic risk of composite likelihood estimators in exponential families.
  This allows us to compare the various estimators.

  @inproceedings{liang08asymptotics,
    author = {Percy Liang and Michael I. Jordan},
    booktitle = {International Conference on Machine Learning (ICML)},
    pages = {584--591},
    title = {An Asymptotic Analysis of Generative, Discriminative, and Pseudolikelihood Estimators},
    year = {2008},
  }
  

  [abstract] [brief] [bib] [paper] [slides]
  
• Structure compilation: trading structure for features. Percy Liang, Hal {Daum{é} III}, Dan Klein. International Conference on Machine Learning (ICML), 2008.

  Structured models often achieve excellent performance but can be slow at test time. We investigate structure compilation, where we replace structure with features, which are often computationally simpler but unfortunately statistically more complex. We analyze this tradeoff theoretically and empirically on three natural language processing tasks. We also introduce a simple method to transfer predictive power from structure to features via unlabeled data, while incurring a minimal statistical penalty.

  How much do we lose by throwing out edge features in CRFs and adding node features?
  Studies the approximation, estimation, computational aspects of the tradeoff.

  @inproceedings{liang08structure,
    author = {Percy Liang and Hal {Daum{é} III} and Dan Klein},
    booktitle = {International Conference on Machine Learning (ICML)},
    title = {Structure Compilation: Trading Structure for Features},
    year = {2008},
  }
  

  [abstract] [brief] [bib] [paper] [slides]
  
• Analyzing the errors of unsupervised learning. Percy Liang, Dan Klein. Human Language Technology and Association for Computational Linguistics (HLT/ACL), 2008.

  We identify four types of errors that unsupervised induction systems make and study each one in turn. Our contributions include (1) using a meta-model to analyze the incorrect biases of a model in a systematic way, (2) providing an efficient and robust method of measuring distance between two parameter settings of a model, and (3) showing that local optima issues which typically plague EM can be somewhat alleviated by increasing the number of training examples. We conduct our analyses on three models: the HMM, the PCFG, and a simple dependency model.

  Error decomposition: approximation, identifiability, estimation, optimization errors.
  Used meta-model to analyze approximation error.
  Empirically observed that more data reduces optimization error.

  @inproceedings{liang08errors,
    author = {Percy Liang and Dan Klein},
    booktitle = {Human Language Technology and Association for Computational Linguistics (HLT/ACL)},
    title = {Analyzing the Errors of Unsupervised Learning},
    year = {2008},
  }
  

  [abstract] [brief] [bib] [paper] [slides]
  
• Learning bilingual lexicons from monolingual corpora. Aria Haghighi, Percy Liang, Taylor Berg-Kirkpatrick, Dan Klein. Human Language Technology and Association for Computational Linguistics (HLT/ACL), 2008.

  We present a method for learning bilingual translation lexicons from monolingual corpora. Word types in each language are characterized by purely monolingual features, such as context counts and orthographic substrings. Translations are induced using a generative model based on canonical correlation analysis, which explains the monolingual lexicons in terms of latent matchings. We show that high-precision lexicons can be learned in a variety of language pairs and from a range of corpus types.

  By using CCA, can do word alignment without the usual sentence-aligned corpora.

  @inproceedings{haghighi08lexicon,
    author = {Aria Haghighi and Percy Liang and Taylor Berg-Kirkpatrick and Dan Klein},
    booktitle = {Human Language Technology and Association for Computational Linguistics (HLT/ACL)},
    title = {Learning Bilingual Lexicons from Monolingual Corpora},
    year = {2008},
  }
  

  [abstract] [brief] [bib] [paper] [code]
  
• Agreement-Based learning. Percy Liang, Dan Klein, Michael I. Jordan. Advances in Neural Information Processing Systems (NeurIPS), 2008.

  The learning of probabilistic models with many hidden variables and non-decomposable dependencies is an important and challenging problem. In contrast to traditional approaches based on approximate inference in a single intractable model, our approach is to train a set of tractable submodels by encouraging them to agree on the hidden variables. This allows us to capture non-decomposable aspects of the data while still maintaining tractability. We propose an objective function for our approach, derive EM-style algorithms for parameter estimation, and demonstrate their effectiveness on three challenging real-world learning tasks.

  Setting: unsupervised learning.
  Alternative to approximate inference: make two tractable models and train them to agree.
  Advantage: maintain existing tractable inference procedures as black-boxes.

  @inproceedings{liang08agreement,
    author = {Percy Liang and Dan Klein and Michael I. Jordan},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    title = {Agreement-Based Learning},
    year = {2008},
  }
  

  [abstract] [brief] [bib] [paper] [poster]
  
• A probabilistic approach to language change. Alexandre Bouchard-Côté, Percy Liang, Tom Griffiths, Dan Klein. Advances in Neural Information Processing Systems (NeurIPS), 2008.

  We present a probabilistic approach to language change in which word forms are represented by phoneme sequences that undergo stochastic edits along the branches of a phylogenetic tree. This framework combines the advantages of the classical comparative method with the robustness of corpus-based probabilistic models. We use this framework to explore the consequences of two different schemes for defining probabilistic models of phonological change, evaluating these schemes by reconstructing ancient word forms of Romance languages. The result is an efficient inference procedure for automatically inferring ancient word forms from modern languages, which can be generalized to support inferences about linguistic phylogenies.

  Feature-based generative model of phonemes of words in a phylogeny of languages.

  @inproceedings{bouchard08language,
    author = {Alexandre Bouchard-Côté and Percy Liang and Tom Griffiths and Dan Klein},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    title = {A Probabilistic Approach to Language Change},
    year = {2008},
  }
  

  [abstract] [brief] [bib] [paper] [poster]
  

2007

• Structured Bayesian nonparametric models with variational inference (tutorial). Percy Liang, Dan Klein. Association for Computational Linguistics (ACL), 2007.

  @inproceedings{liang07tutorial,
    author = {Percy Liang and Dan Klein},
    booktitle = {Association for Computational Linguistics (ACL)},
    title = {Structured {B}ayesian Nonparametric Models with Variational Inference (tutorial)},
    year = {2007},
  }
  

  [bib] [paper] [slides]
  
• A permutation-augmented sampler for Dirichlet process mixture models. Percy Liang, Michael I. Jordan, Ben Taskar. International Conference on Machine Learning (ICML), 2007.

  We introduce a new inference algorithm for Dirichlet process mixture models. While Gibbs sampling and variational methods focus on local moves, the new algorithm makes more global moves. This is done by introducing a permutation of the data points as an auxiliary variable. The algorithm is a blocked sampler which alternates between sampling the clustering and sampling the permutation. The key to the efficiency of this approach is that it is possible to use dynamic programming to consider all exponentially many clusterings consistent with a given permutation. We also show that random projections can be used to effectively sample the permutation. The result is a stochastic hill-climbing algorithm that yields burn-in times significantly smaller than those of collapsed Gibbs sampling.

  Task: clustering.
  Idea: conditioned on a permutation of the data points, one can consider all possible clusterings of those data points which are consistent with the permutation using dynamic programming.
  Idea: if data are ordered, can cluster using dynamic programming.
  Let this ordering be a random auxiliary variable and we get a sampler.

  @inproceedings{liang07permdp,
    author = {Percy Liang and Michael I. Jordan and Ben Taskar},
    booktitle = {International Conference on Machine Learning (ICML)},
    title = {A permutation-augmented sampler for {D}irichlet process mixture models},
    year = {2007},
  }
  

  [abstract] [brief] [bib] [paper] [slides]
  
• The infinite PCFG using hierarchical Dirichlet processes. Percy Liang, Slav Petrov, Michael I. Jordan, Dan Klein. Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP/CoNLL), 2007.

  We present a nonparametric Bayesian model of tree structures based on the hierarchical Dirichlet process (HDP). Our HDP-PCFG model allows the complexity of the grammar to grow as more training data is available. In addition to presenting a fully Bayesian model for the PCFG, we also develop an efficient variational inference procedure. On synthetic data, we recover the correct grammar without having to specify its complexity in advance. We also show that our techniques can be applied to full-scale parsing applications by demonstrating its effectiveness in learning state-split grammars.

  A PCFG with an infinite number of states.
  Learning: variational inference.

  @inproceedings{liang07infpcfg,
    author = {Percy Liang and Slav Petrov and Michael I. Jordan and Dan Klein},
    booktitle = {Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP/CoNLL)},
    title = {The Infinite {PCFG} using Hierarchical {D}irichlet Processes},
    year = {2007},
  }
  

  [abstract] [brief] [bib] [paper] [slides]
  
• A probabilistic approach to diachronic phonology. Alexandre Bouchard-Côté, Percy Liang, Tom Griffiths, Dan Klein. Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP/CoNLL), 2007.

  We present a probabilistic model of diachronic phonology in which individual word forms undergo stochastic edits along the branches of a phylogenetic tree. Our approach allows us to achieve three goals with a single unified model: (1) reconstruction of both ancient and modern word forms, (2) discovery of general phonological changes, and (3) selection among different phylogenies. We learn our model using a Monte Carlo EM algorithm and present quantitative results validating the model.

  Generative model of phonemes of words in a phylogeny of languages

  @inproceedings{bouchard07diachronic,
    author = {Alexandre Bouchard-Côté and Percy Liang and Tom Griffiths and Dan Klein},
    booktitle = {Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP/CoNLL)},
    title = {A Probabilistic Approach to Diachronic Phonology},
    year = {2007},
  }
  

  [abstract] [brief] [bib] [paper]
  

2006

• An end-to-end discriminative approach to machine translation. Percy Liang, Alexandre Bouchard-Côté, Dan Klein, Ben Taskar. International Conference on Computational Linguistics and Association for Computational Linguistics (COLING/ACL), 2006.

  We present a perceptron-style discriminative approach to machine translation in which large feature sets can be exploited. Unlike discriminative reranking approaches, our system can take advantage of learned features in all stages of decoding. We first discuss several challenges to error-driven discriminative approaches. In particular, we explore different ways of updating parameters given a training example. We find that making frequent but smaller updates is preferable to making fewer but larger updates. Then, we discuss an array of features and show both how they quantitatively increase BLEU score and how they qualitatively interact on specific examples. One particular feature we investigate is a novel way to introduce learning into the initial phrase extraction process, which has previously been entirely heuristic.

  Task: machine translation.
  Idea: treat machine translation as a structured classification task (learn a map from input sentence to output sentence). Use a Perceptron-like algorithm: decode and update towards maximum BLEU scoring translation on the n-best list.

  @inproceedings{liang06discrimative,
    author = {Percy Liang and Alexandre Bouchard-Côté and Dan Klein and Ben Taskar},
    booktitle = {International Conference on Computational Linguistics and Association for Computational Linguistics (COLING/ACL)},
    title = {An End-to-End Discriminative Approach to Machine Translation},
    year = {2006},
  }
  

  [abstract] [brief] [bib] [paper] [slides]
  
• Alignment by agreement. Percy Liang, Ben Taskar, Dan Klein. North American Association for Computational Linguistics (NAACL), 2006.

  We present an unsupervised approach to symmetric word alignment in which two simple asymmetric models are trained jointly to maximize a combination of data likelihood and agreement between the models. Compared to the standard practice of intersecting predictions of independently-trained models, joint training provides a 32% reduction in AER. Moreover, a simple and efficient pair of HMM aligners provides a 29% reduction in AER over symmetrized IBM model 4 predictions.

  Task: unsupervised word alignment.
  Idea: Jointly train two HMM models (one in each direction) to encourage agreement. Uses a simple EM-like algorithm for training.
  Result: performance competitive with supervised methods (4.9 AER on Hansards).

  @inproceedings{liang06alignment,
    author = {Percy Liang and Ben Taskar and Dan Klein},
    booktitle = {North American Association for Computational Linguistics (NAACL)},
    pages = {104--111},
    title = {Alignment by Agreement},
    year = {2006},
  }
  

  [abstract] [brief] [bib] [paper] [slides] [code]
  

2005

• Semi-Supervised learning for natural language. Percy Liang. Massachusetts Institute of Technology, 2005.

  Task: named-entity recognition and Chinese word segmentation
  Idea: create features based on unlabeled data to use in Perceptron learning in Markov or semi-Markov models

  @mastersthesis{liang05meng,
    author = {Percy Liang},
    school = {Massachusetts Institute of Technology},
    title = {Semi-Supervised Learning for Natural Language},
    year = {2005},
  }
  

  [brief] [bib] [paper] [errata]
  
• A data structure for maintaining acyclicity in hypergraphs. Percy Liang, Nathan Srebro. Massachusetts Institute of Technology Technical Report, 2005.

  We introduce the first definition of hyperacyclicity for hypergraphs, a generalization of acyclicity in graphs.
  We provide a dynamic data structure for maintaining hyperacyclicity, a generalization of Tarjan's Union-Find algorithm.

  @techreport{liang05hypercycle,
    author = {Percy Liang and Nathan Srebro},
    institution = {Massachusetts Institute of Technology},
    title = {A Data Structure for Maintaining Acyclicity in Hypergraphs},
    year = {2005},
  }
  

  [brief] [bib] [paper] [code]
  
• Linear programming in bounded tree-width Markov networks. Percy Liang, Nathan Srebro. Mathematical Programing for Data Mining and Machine Learning Workshop at McMaster University, 2005.

  @inproceedings{liang05mcmaster,
    author = {Percy Liang and Nathan Srebro},
    booktitle = {Mathematical Programing for Data Mining and Machine Learning Workshop at McMaster University},
    title = {Linear Programming in Bounded Tree-width {M}arkov Networks},
    year = {2005},
  }
  

  [bib] [slides] [code]
  
• Efficient geometric algorithms for parsing in two dimensions. Percy Liang, Mukund Narasimhan, Michael Shilman, Paul Viola. International Conference on Document Analysis and Recognition (ICDAR), 2005.

  In parsing sequences using dynamic programming, the subproblems are continguous subsequences (quadratic in number of terminals). In parsing documents or images, the subproblems would be subsets of the terminals (exponential in number of terminals). We introduce (and unify) several ways to constrain these subsets using the geometric structure of the terminals.

  @inproceedings{liang05geometric,
    author = {Percy Liang and Mukund Narasimhan and Michael Shilman and Paul Viola},
    booktitle = {International Conference on Document Analysis and Recognition (ICDAR)},
    title = {Efficient Geometric Algorithms for Parsing in Two Dimensions},
    year = {2005},
  }
  

  [brief] [bib] [paper]
  

2004

• Methods and experiments with bounded tree-width Markov networks. Percy Liang, Nathan Srebro. Massachusetts Institute of Technology Technical Report, 2004.

  Use a greedy procedure to find the maximum likelihood (or MDL) bounded tree-width Markov network (for tree-width 1, equivalent to Chow-Liu maximum spanning trees).

  @techreport{liang04markov,
    author = {Percy Liang and Nathan Srebro},
    institution = {Massachusetts Institute of Technology},
    title = {Methods and Experiments With Bounded Tree-width {M}arkov Networks},
    year = {2004},
  }
  

  [brief] [bib] [paper] [code]
  

2003

• How much of a hypertree can be captured by windmills? Percy Liang, Nathan Srebro. Massachusetts Institute of Technology Technical Report, 2003.

  Use linear programming to find worst case inputs to a dynamic program in order to explore the tightness of a bound for approximating maximum weight hypertrees with windmill farms.

  @techreport{liang03maxwmfarm,
    author = {Percy Liang and Nathan Srebro},
    institution = {Massachusetts Institute of Technology},
    title = {How Much Of A Hypertree Can Be Captured By Windmills?},
    year = {2003},
  }
  

  [brief] [bib] [paper] [code]