Fei Fang

Persuasive Prediction via Decision Calibration

AI Realtor: Towards Grounded Persuasive Language Generation for Automated Copywriting

Strategic Planning and Rationalizing on Trees Make LLMs Better Debaters

Not All Rollouts are Useful: Down-Sampling Rollouts in LLM Reinforcement Learning

Learning Instruction-Following Policies through Open-Ended Instruction Relabeling with Large Language Models

M³HF: Multi-agent Reinforcement Learning from Multi-phase Human Feedback of Mixed Quality

LICORICE: Label-Efficient Concept-Based Interpretable Reinforcement Learning

TypedThinker: Diversify Large Language Model Reasoning with Typed Thinking

Incorporating Human Preferences into Interpretable Reinforcement Learning with Tree Policies