Gradient-Stable Attention Heads Signal LLM Correctness

Abstract:Large language models (LLMs) often generate plausible yet incorrect answers, posing risks in safety-critical settings such as medicine. Human evaluation is expensive, and LLM-as-judge approaches risk introducing hidden errors. Recent single-pass white-box methods detect contextual hallucinations using linear probes over model internals, but their generalization to out-of-domain, out-of-task, and training-free settings remains poorly understood. We introduce HeadEntropy, a method that predicts answer correctness by measuring how susceptible each attention head's pattern is to modification under further gradient updates. The key insight is that the trace of the softmax Jacobian is a monotonic function of 2-Renyi entropy, linking attention spread to gradient stability during training, even without the reference annotation. With no training, HeadEntropy reaches 0.736 AUROC, outperforms every training-free baseline in paired comparison and matches a hidden-state probe out-of-domain, at under 1% of inference cost. We evaluate broadly across 5 instruction-tuned LLMs and 5 datasets spanning general knowledge, multi-hop reasoning, mathematical reasoning, claim verification, and medicine. The code is available at this https URL.

Machine Learning (cs.LG)

arXiv:2602.13699 [cs.LG]

(or arXiv:2602.13699v2 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2602.13699 Focus to learn more arXiv-issued DOI via DataCite

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.