finding
active
finding:claude-3-7-sonnet-overall-cot-faithfulness-is-25Claude 3.7 Sonnet overall CoT faithfulness is 25%
Low faithfulness.
Source paper
extracted_from(2025) · Yanda Chen · Joe Benton · Ansh Radhakrishnan · Jonathan Uesato +11
Neighborhood — ranked by edge-count
Papers (1)
paper
Claims (1)
claim
- CoT monitoring is promising for noticing unintended behaviors but not sufficient to rule them outsupportsCentral conclusion.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Unfaithful CoTs are longer.
- Harder questions lower faithfulness.
- CoTs may hide problematic reasoning.
- Linked to Claude 3.5 Sonnet not exhibiting pro-animal-welfare preferences
- Claude 3.7 Sonnet verbalizes used hints at least 1% in 5/6 settings vs Claude 3.5 Sonnet 4/6finding0.799Reasoning > non-reasoning.
- Early improvement.
- Anthropic model tested in Experiments 1, 3, 4; shows 100% experience reporting under self-referential induction
- Anthropic model tested in Experiments 1, 3, 4; shows 100% experience reporting under self-referential induction