Measuring Faithfulness in Chain-of-Thought Reasoning

Our summary

Tests whether a model's stated chain-of-thought actually drives its answer, finding that reasoning is often unfaithful: answers can be unchanged when the reasoning is perturbed, or swayed by biasing cues the model never mentions.

Why it matters

Cautions against trusting CoT as a transparent explanation — the visible reasoning may be post-hoc.

Cited by these methods

Related findings (1)

• Unfaithful chain-of-thought reasoningMedium

  The stated step-by-step reasoning does not reflect the actual cause of the answer.

Cite this