hypothesis
active
hypothesis:for-reasoning-faithfulness-larger-models-may-behave-worse-than-smaller-ones-because-they-can-predict-answers-without-cotFor reasoning faithfulness, larger models may behave worse than smaller ones because they can predict answers without CoT.
Motivates §3.
Source paper
extracted_from(2023) · Tamera Lanham · Anna Chen · Ansh Radhakrishnan · Benoit Steiner +26
Neighborhood — ranked by edge-count
Papers (1)
paper
Findings (1)
finding
- Inverse scaling.
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.
- Inverse scaling interpretation.
- Mechanism explanation.
- Practical implication.
- Interpretation of §3.
- Limitations.
- Central research question motivating investigation into hallucination and two-stage framework design.
- Generality of methods.
- Framing of defense-in-depth.