claim
active
claim:the-proposed-faithfulness-tests-should-hold-for-other-reasoning-elicitation-methods-tree-of-thoughts-plan-and-solve-debate-subquestions-that-share-cot-s-structureThe proposed faithfulness tests should hold for other reasoning-elicitation methods (tree of thoughts, plan-and-solve, debate, subquestions) that share CoT's structure.
Generality of methods.
Source paper
extracted_from(2023) · Tamera Lanham · Anna Chen · Ansh Radhakrishnan · Benoit Steiner +26
Neighborhood — ranked by edge-count
Papers (1)
paper
- Measuring Faithfulness in Chain-of-Thought Reasoningmentionssupports
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.
- Framing of defense-in-depth.
- Varying the hint changes the motivated-reasoning CoT endpoint, while the faithful case always yields 8.finding0.829Tests bias susceptibility.
- For reasoning faithfulness, larger models may behave worse than smaller ones because they can predict answers without CoT.hypothesis0.823Motivates §3.
- Interpretation of §3.
- Mechanism explanation.
- Practical implication.
- Limitations.
- Proof of concept.