Score: 1

Doubly Robust Alignment for Large Language Models

Published: June 1, 2025 | arXiv ID: 2506.01183v1

By: Erhan Xu , Kai Ye , Hongyi Zhou and more

Potential Business Impact:

Makes AI understand what people want better.

Business Areas:
A/B Testing Data and Analytics

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

Repos / Data Links

Page Count
44 pages

Category
Computer Science:
Machine Learning (CS)