Discovering Factor Level Preferences to Improve Human-Model Alignment
Keywords: human alignment, Large Language Model, explainability, generation, evaluation
TL;DR: Through factor-level probing of preferences, we show that LLM generations are not yet aligned to human preferences
Abstract: Despite advancements in Large Language Model (LLM) alignment, understanding the reasons behind LLM preferences remains crucial for bridging the gap between desired and actual behavior. LLMs often exhibit biases or tendencies that diverge from human preferences, such as favoring certain writing styles or producing overly verbose outputs. However, current methods for evaluating preference alignment often lack explainability, relying on coarse-grained comparisons. To address this, we introduce PROFILE (PRObing Factors of InfLuence for Explainability), a novel framework that uncovers and quantifies the influence of specific factors driving preferences. PROFILE's factor level analysis explains the "why" behind human-model alignment and misalignment, offering insights into the direction of model improvement. We apply PROFILE to analyze human and LLM preferences across three tasks: summarization, helpful response generation, and document-based question-answering. Our factor level analysis reveals a substantial discrepancy between human and LLM preferences in generation tasks, whereas LLMs show strong alignment with human preferences in evaluation tasks. We demonstrate how leveraging factor level insights, including addressing misaligned factors or exploiting the generation-evaluation gap, can improve alignment with human preferences. This work underscores the importance of explainable preference analysis and highlights PROFILE's potential to provide valuable training signals, driving further improvements in human-LLM alignment.
Primary Area: interpretability and explainable AI
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: 13360
Loading