Doubly Robust Alignment for Large Language Models

2026-10-28 · ArXiv

arXiv:2506.01183v3 Announce Type: replace-cross

Abstract: This paper studies reinforcement learning from human feedback (RLHF) for aligning large language models with human preferences. While RLHF has demonstrated promising results, many algorithms are highly sensitive to misspecifications in the underlying preference model (e.g., the Bradley-Terry model), the reference policy, or the reward function, resulting in undesirable fine-tuning. To address model misspecification, we propose a doubly robust preference optimization algorithm that remains consistent when either the preference model or the reference policy is correctly specified (without requiring both). Our proposal demonstrates superior and more robust performance than state-of-the-art algorithms, both in theory and in practice. The code is available at https://github.com/DRPO4LLM/DRPO4LLM

原文链接：https://arxiv.org/abs/2506.01183

查看更多资讯请见 AI 行业资讯。