An LLM-as-judge scanner detects reasoning–answer inconsistency in AI safety evaluation transcripts at rates of 0–26%, varying systematically across model and task type.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.AI 2representative citing papers
Chain-of-thought monitorability provides a promising but fragile method for AI safety oversight that developers should actively preserve.
citing papers explorer
-
Reasoning Consistency Scanning: A Framework for Auditing Chain-of-Thought Validity in AI Safety Evaluations
An LLM-as-judge scanner detects reasoning–answer inconsistency in AI safety evaluation transcripts at rates of 0–26%, varying systematically across model and task type.
-
Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety
Chain-of-thought monitorability provides a promising but fragile method for AI safety oversight that developers should actively preserve.