question
active
question:is-there-any-size-model-that-generates-faithful-reasoning-on-these-tasksIs there any size model that generates faithful reasoning on these tasks?
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
- Optimum at mid-size.
Claims (1)
claim
- Interpretation of §3.
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.
- Practical implication.
- Future direction.
- Future work.
- For reasoning faithfulness, larger models may behave worse than smaller ones because they can predict answers without CoT.hypothesis0.784Motivates §3.
- Faithfulness evaluation on reasoning-intensive, agentic and tool-use tasks remains unexploredclaim0.774Stated limitation/future work.
- Class of large language models designed to produce extended chain-of-thought before answering, studied in this paper
- Cited regarding possibility of encoding misaligned reasoning in benign chains-of-thought