Thinking-mode VLMs collapse answer-token entropy, but thinking-chain entropy and length serve as robust, zero-cost hallucination predictors.
Nature , volume=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 2years
2026 2roles
background 1polarities
background 1representative citing papers
EPGS detects high-confidence factual errors in LLMs by using embedding perturbations to measure gradient sensitivity as a proxy for sharp versus flat minima.
citing papers explorer
-
When Thinking Hurts: Epistemic Signals in the Reasoning Chains of Visual Language Models
Thinking-mode VLMs collapse answer-token entropy, but thinking-chain entropy and length serve as robust, zero-cost hallucination predictors.
-
From Flat Facts to Sharp Hallucinations: Detecting Stubborn Errors via Gradient Sensitivity
EPGS detects high-confidence factual errors in LLMs by using embedding perturbations to measure gradient sensitivity as a proxy for sharp versus flat minima.