← Back to The Lab
About
Dr. Lin Wei researches reinforcement learning from human feedback and the evaluation of frontier language models. Her recent work focuses on preference modeling, reward hacking, and rigorous holistic evaluation suites.
Education & Background
- •Ph.D. in Machine Learning, University of Toronto
- •B.S. in Statistics, Tsinghua University
Active RFPs
Published Papers
- Reward hacking in long-horizon RLHF— ICLR 2024
- Calibrated preference modeling— NeurIPS 2023