CoT probe-time gains arise primarily from lexical activation and short-range token co-occurrence rather than sentence-level logical derivation.
Rethinking chain-of- thought from the perspective of self-training.arXiv preprint arXiv:2412.10827, 2024
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.AI 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Semi-CoT selects low-entropy pseudo-CoT chains from unlabeled questions via answer-level semantic entropy and shows high pseudo-answer precision but only small or negative gains on math reasoning benchmarks.
citing papers explorer
-
What Makes Chain-of-Thought Work at Probe Time? Local Co-occurrence Rather Than Global Derivation
CoT probe-time gains arise primarily from lexical activation and short-range token co-occurrence rather than sentence-level logical derivation.
-
Revisiting Chain-of-Thought Reasoning under Limited Supervision: Semi-supervised Chain-of-Thought Learning
Semi-CoT selects low-entropy pseudo-CoT chains from unlabeled questions via answer-level semantic entropy and shows high pseudo-answer precision but only small or negative gains on math reasoning benchmarks.