hypothesis
active
hypothesis:models-might-be-trained-smaller-to-specialize-for-reasoning-tasksModels might be trained smaller to specialize for reasoning tasks
Future direction.
Source paper
extracted_from(2025) · Merullo, Jack · Vatsavaya, Srihita · Bushnaq, Lucius · Lewis, Owen
Neighborhood — ranked by edge-count
Papers (1)
paper
Claims (1)
claim
- Abstract thesis.
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.
- Selective pressure toward convergence via task generality
- Practical implication.
- Core goal statement.
- Core framing.
- Class of large language models designed to produce extended chain-of-thought before answering, studied in this paper
- Practical interpretive upshot connecting dynamics to model competence.
- Motivates §3.