Collaborative Gym: A Framework for Enabling and Evaluating Human-Agent Collaboration

PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action

Into the Unknown Unknowns: Engaged Human Learning through Participation in Language Model Agent Conversations

Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking

Show, Don't Tell: Aligning Language Models with Demonstrated Feedback

Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models

Class Incremental Learning via Likelihood Ratio Based Task Prediction

Class-Incremental Learning based on Label Generation

ACCENT: An Automatic Event Commonsense Evaluation Metric for Open-Domain Dialogue Systems

Continual Pre-training of Language Models

FormLM: Recommending Creation Ideas for Online Forms by Modeling Semantic and Structural Information

Adapting a Language Model While Preserving its General Knowledge

Continual Training of Language Models for Few-Shot Learning

CMG: A Class-Mixed Generation Approach to Out-of-Distribution Detection