Direct Preference Optimization With Unobserved Preference Heterogeneity
Keywords: RLHF, LLM Alignment, Preference Aggregation
TL;DR: Algorithm to directly train a single equitable policy from heterogeneous preferences without reward models.
Abstract: RLHF has emerged as a pivotal step in aligning language models with human objectives and values. It typically involves learning a reward model from human preference data and then using reinforcement learning to update the generative model accordingly. Conversely, Direct Preference Optimization (DPO) directly optimizes the generative model with preference data, skipping reinforcement learning. However, both RLHF and DPO assume uniform preferences, overlooking the reality of diverse human annotators. This paper presents a new method to align generative models with varied human preferences. We propose an Expectation-Maximization adaptation to DPO, generating a mixture of models based on latent preference types of the annotators. We then introduce a min-max regret ensemble learning model to produce a single generative method to minimize worst-case regret among annotator subgroups with similar latent factors. Our algorithms leverage the simplicity of DPO while accommodating diverse preferences. Experimental results validate the effectiveness of our approach in producing equitable generative policies.
Primary Area: reinforcement learning
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 12279
Loading