Style Outweighs Substance: Failure Modes of LLM Judges in Alignment Benchmarking
Keywords: LLM, large language model, alignment, post-training, benchmarking, evaluation
TL;DR: We find that LLM judgments do not correlate with concrete measures of alignment, and that LLM judges have powerful implicit biases, prioritizing style over factuality and safety.
Abstract: The release of ChatGPT in November 2022 sparked an explosion of interest in post-training and an avalanche of new preference optimization (PO) methods. These methods claim superior alignment by virtue of better correspondence with human pairwise preferences, often measured by LLM-judges. In this work, we attempt to answer the following question -- do LLM-judge preferences translate to progress on other, more concrete metrics for alignment, and if not, why not? We define a concrete metric for alignment, and introduce SOS-Bench (Substance Outweighs Style Benchmark), the largest standardized, reproducible LLM meta-benchmark to date. We find that (1) LLM-judge preferences do not correlate with concrete measures of safety, world knowledge, and instruction following; (2) LLM-judges have powerful implicit biases, prioritizing style over factuality and safety; and (3) the supervised fine-tuning (SFT) stage of post-training has a large impact on alignment, with data scaling and prompt diversity as the driving factors.
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.
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: 3098
Loading