Mitigating Bias in Reinforcement Learning from Human Feedback for Large Language Models

Authors: C Ravulu, R Sarabu, M Suryadevara

Published: 2024

Publication: ... Conference on AI x ..., 2024 - ieeexplore.ieee.org

Research paper: Mitigating Bias in Reinforcement Learning from Human Feedback for Large Language Models

Institution: International Institute of Information Technology, University of California Santa Cruz, University of South Carolina Aiken

Research Area: Reinforcement Learning from Human Feedback (RLHF), Bias Mitigation, LLM, AI Bias

Discipline: Artificial Intelligence

DOI: https://ieeexplore.ieee.org/abstract/document/10990073/