Hybrid Preferences: Learning to Route Instances for Human vs. AI Feedback
Keywords: Preference Learning, RLHF, AI Feedback, Language Models
Abstract: Learning from human feedback has enabled the alignment of language models (LMs) with human preferences. However, directly collecting human preferences can be expensive, time-consuming, and can have high variance. An appealing alternative is to distill preferences from LMs as a source of synthetic annotations as they are more consistent, cheaper, and scale better than human annotation; however, they are also prone to biases and errors. In this work, we introduce a routing framework that combines inputs from humans and LMs to achieve better annotation quality, while reducing the total cost of human annotation. The crux of our approach is to identify preference instances that will benefit from human annotations. We formulate this as an optimization problem: given a preference dataset and an evaluation metric, we train a performance prediction model to predict a reward model's performance on an arbitrary combination of human and LM annotations and employ a routing strategy that selects a combination that maximizes predicted performance. We train the performance prediction model on MultiPref, a new preference dataset with 10K instances paired with human and LM labels. We show that the selected hybrid mixture of LM and direct human preferences using our routing framework achieves better reward model performance compared to using either one exclusively. We simulate selective human preference collection on three other datasets and show that our method generalizes well to all three. We analyze features from the routing model to identify characteristics of instances that can benefit from human feedback, e.g., prompts with a moderate safety concern or moderate intent complexity. We release the dataset, annotation platform, and source code used in this study to foster more efficient and accurate preference collection in the future.
Primary Area: foundation or frontier models, including LLMs
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: 8938
Loading