ASMI, an attention-head masking mutual information score, adds error-predictive power beyond confidence and entropy on grounded QA and degrades to chance on parametric recall, matching its design prediction.
Proceedings of EMNLP: System Demonstrations , pages=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Attention-Path Fragility as an Uncertainty Signal in Large Language Models
ASMI, an attention-head masking mutual information score, adds error-predictive power beyond confidence and entropy on grounded QA and degrades to chance on parametric recall, matching its design prediction.