Spread Preference Annotation: Direct Preference Judgment for Efficient LLM Alignment
Keywords: large language model, alignment, preference
Abstract: Aligning large language models (LLMs) with human preferences becomes a key component to obtaining state-of-the-art performance, but it yields a huge cost to construct a large human-annotated preference dataset. To tackle this problem, we propose a new framework, Spread Preference Annotation with direct preference judgment (SPA), that boosts the alignment of LLMs using only a very small amount of human-annotated preference data.
Our key idea is leveraging the human prior knowledge within the small (seed) data and progressively improving the alignment of LLM, by iteratively generating the responses and learning from them with the self-annotated preference data.
To be specific, we propose to derive the preference label from the logits of LLM to explicitly extract the model's inherent preference.
Compared to the previous approaches using external reward models or implicit in-context learning, we observe that the proposed approach is significantly more effective.
In addition, we introduce a noise-aware preference learning algorithm to mitigate the risk of low quality within generated preference data.
Our experimental results demonstrate that the proposed framework significantly boosts the alignment of LLMs.
For example, we achieve superior alignment performance on AlpacaEval 2.0 with only 3.3% of the ground-truth preference labels in the Ultrafeedback data compared to the cases using the entire data or state-of-the-art baselines.
Primary Area: generative models
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: 12928
Loading