CoT traces align with internal answer commitment in only 61.9% of steps on average, dominated by confabulated continuations after commitment has stabilized.
Mechanistic evidence for faithfulness decay in chain-of-thought reasoning
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 2polarities
background 2representative citing papers
SLRC quantifies genuine step necessity in LLM reasoning as a causal estimator, LC-CoSR training reduces rigidity with stability guarantees, and evaluations reveal a faithfulness-sycophancy paradox across frontier models.
LLM reasoning is primarily mediated by latent-state trajectories rather than by explicit surface chain-of-thought outputs.
citing papers explorer
-
When Reasoning Traces Become Performative: Step-Level Evidence that Chain-of-Thought Is an Imperfect Oversight Channel
CoT traces align with internal answer commitment in only 61.9% of steps on average, dominated by confabulated continuations after commitment has stabilized.
-
Measuring and curing reasoning rigidity: from decorative chain-of-thought to genuine faithfulness
SLRC quantifies genuine step necessity in LLM reasoning as a causal estimator, LC-CoSR training reduces rigidity with stability guarantees, and evaluations reveal a faithfulness-sycophancy paradox across frontier models.
-
LLM Reasoning Is Latent, Not the Chain of Thought
LLM reasoning is primarily mediated by latent-state trajectories rather than by explicit surface chain-of-thought outputs.