Author

Brian Axelrod

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Feb 2026

Gradient-Stable Attention Heads Signal LLM Correctness

This work introduces HeadEntropy, a method that predicts answer correctness by measuring how susceptible each attention head's pattern is to modification under further gradient updates, and evaluates broadly across 5 instruction-tuned LLMs and 5 datasets spanning general knowledge, multi-hop reasoning, mathematical rea...

S. Ostmeier, Brian Axelrod, M. Varma et al. · 5 citations