How Reliable Is Human Feedback For Aligning Large Language Models?
Keywords: Human feedback, LLM alignment, Qualitative analysis
Abstract: Most alignment research today focuses on designing new learning algorithms using datasets like Anthropic-HH, assuming human feedback data is inherently reliable. However, little attention has been given to the qualitative unreliability of human feedback and its impact on alignment. To address this gap, we conduct a comprehensive study and provide an in-depth analysis of human feedback data. We assess feedback reliability using a committee of gold reward models, revealing that over 25% of the dataset shows low or no agreement with these models, implying a high degree of unreliability. Through a qualitative analysis, we identify six key sources of unreliability, such as mis-labeling, subjective preferences, differing criteria and thresholds for helpfulness and harmlessness, etc. Lastly, to mitigate unreliability, we propose Source-Aware Cleaning, an automatic data-cleaning method guided by the insight of our qualitative analysis, to significantly improve data quality. Extensive experiments demonstrate that models trained on our cleaned dataset, HH-Clean, substantially outperform those trained on the original dataset. We release HH-Clean to support more reliable LLM alignment research in the future.
Primary Area: alignment, fairness, safety, privacy, and societal considerations
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: 2516
Loading