A training-free and label-free detector of cyclic hidden-state patterns triggers early exit during chain-of-thought reasoning, reducing token length while mostly preserving or improving accuracy.
Unsuper- vised real-time hallucination detection based on the internal states of large language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CoRE: Enhancing Metacognition with Label-free Self-evaluation in LRMs
A training-free and label-free detector of cyclic hidden-state patterns triggers early exit during chain-of-thought reasoning, reducing token length while mostly preserving or improving accuracy.