Token entropy distributions fingerprint hallucinations in generative models, enabling the Calibrated Entropy Score (CES) for single-pass black-box detection with calibration guarantees via a novel DKW inequality.
& Sattigeri, P
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
Trajectory geometry in embedding space fused with coverage and verbalization yields better black-box CoT confidence estimation than self-consistency at lower sample counts across six benchmark-reasoner pairs.
LLMs show improved accuracy on gastroenterology questions but remain overconfident in self-reported certainty across commercial, open-source, and quantized variants.
citing papers explorer
-
Entropy Distribution as a Fingerprint for Hallucinations in Generative Models
Token entropy distributions fingerprint hallucinations in generative models, enabling the Calibrated Entropy Score (CES) for single-pass black-box detection with calibration guarantees via a novel DKW inequality.
-
Measuring Black-Box Confidence via Reasoning Trajectories: Geometry, Coverage, and Verbalization
Trajectory geometry in embedding space fused with coverage and verbalization yields better black-box CoT confidence estimation than self-consistency at lower sample counts across six benchmark-reasoner pairs.
-
Self-Reported Confidence of Large Language Models in Gastroenterology: Analysis of Commercial, Open-Source, and Quantized Models
LLMs show improved accuracy on gastroenterology questions but remain overconfident in self-reported certainty across commercial, open-source, and quantized variants.