Distilled-reasoning models actively depend on chain-of-thought for soft reasoning tasks, and a chain's causal influence can diverge from its explanatory faithfulness.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Analysing Chain of Thought Dynamics: Active Guidance or Unfaithful Post-hoc Rationalisation?
Distilled-reasoning models actively depend on chain-of-thought for soft reasoning tasks, and a chain's causal influence can diverge from its explanatory faithfulness.