Yijia Shao


I am a 1st-year PhD student at Stanford NLP advised by Diyi Yang. I also work closely with Monica S. Lam and Michael Bernstein. Previously, I was an undergraduate student at Yuanpei College in Peking University where I got into ML and NLP research by working with Bing Liu. In summer 2022 , I had a research internship in UCLA hosted by Nanyun Peng. Before that, I have worked as a research intern with Mengyu Zhou in Microsoft Research Asia (blog spotlight in Chinese) and an engineering intern with Tensorflow Lite team in Google, Beijing.

My research interests lie in ML and NLP. Nowadays, I’m interested in positioning NLP models (e.g., LLM) into larger systems. Here are some core problems I’m thinking about:

  • How can NLP models bridge human and systems or systems and systems?
  • How to build socially aware models to ensure safe, comfortable and supportive interaction with users?
  • How to continually improve the models through the interaction with human and external systems?

Many kind people helped me a lot in my journey. If you want to talk more about research or seek advice that I may be able to provide, feel free to email me or book a chat here.

Recent News

  • (Apr, 2024) The code of STORM is now released. Try out our live demo now to see how STORM can help your knowledge exploration journey and please provide feedback to help us improve the system🙏!
  • (Mar, 2024) STORM, a system that writes Wikipedia-like articles based on Internet search, is accepted to NAACL 2024. Check out our preprint and Twitter thread! Working on releasing the demo and our codebase 💪, stay tuned!
  • (Jan, 2024) One paper is accepted by ICLR2024. The work is conducted during my undergraduate study and establishes a link between continual learning and out-of-distribution detection. Check out our preprint and code!
  • (Jul, 2023) Two works on NLP continual learning and evaluation are presented at ACL'23.
  • (Apr, 2023) Guest talk on "Thoughts on NLP Research in the (Post-)LLM Era" at SMS seminar, Peking University. [slides]

Selected Publications

(*: Equal Contribution)

Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models
Yijia Shao, Yucheng Jiang, Theodore A. Kanell, Peter Xu, Omar Khattab, Monica S. Lam
Will appear in NAACL 2024.
Class Incremental Learning via Likelihood Ratio Based Task Prediction
Haowei Lin, Yijia Shao, Weinan Qian, Ningxin Pan, Yiduo Guo, Bing Liu
Will appear in ICLR 2024.
Yijia Shao, Yiduo Guo, Dongyan Zhao, Bing Liu
In ACL 2023.
Sarik Ghazarian*, Yijia Shao*, Rujun Han, Aram Galstyan, Nanyun Peng
In ACL 2023. (also presented in SoCal NLP Symposium 2022)
Zixuan Ke*, Yijia Shao*, Haowei Lin*, Tatsuya Konishi, Gyuhak Kim, Bing Liu
In ICLR 2023.
Yijia Shao, Mengyu Zhou, Yifan Zhong, Tao Wu, Hongwei Han, Gideon Huang, Dongmei Zhang
In EMNLP 2022.
Zixuan Ke, Yijia Shao, Haowei Lin, Hu Xu, Lei Shu, Bing Liu
In EMNLP 2022.
Zixuan Ke, Haowei Lin, Yijia Shao, Hu Xu, Lei Shu, Bing Liu
In EMNLP 2022.
Mengyu Wang*, Yijia Shao*, Haowei Lin, Wenpeng Hu, Bing Liu
In ECML-PKDD 2022.

Selected Awards

  • SenseTime Scholarship, 2022 (awarded to 30 students in China)
  • May 4th Scholarship, 2021 (the highest honor for students in PKU)
  • National Scholarship, 2020, 2022
  • First prize in 12th Chinese Mathematics Competition Final, 2020
  • Merit Student Pacesetter, 2020, 2021, 2022
  • First Class Scholarship for Freshmen of Peking University, 2019