Open problems and fundamental limitations of reinforcement learning from human feedback

Authors: S Casper, X Davies, C Shi, TK Gilbert

Published: 2023

Publication: arXiv preprint arXiv ..., 2023 - arxiv.org

Research paper: Open problems and fundamental limitations of reinforcement learning from human feedback

Institution: Columbia University, Cornell Tech, Apollo Research, ETH Zurich, UC Berkeley, University of Sussex, Independent

Research Area: Reinforcement Learning from Human Feedback (RLHF), Alignment, LLM Limitations

Discipline: Artificial Intelligence

Citations: 848

DOI: https://doi.org/10.48550/arXiv.2307.15217