quote
active
quote:larger-models-enjoy-a-genuine-advantage-that-may-allow-them-to-learn-task-distributions-that-smaller-models-will-inevitably-fail-to-learn-within-the-same-training-setuplarger models enjoy a genuine advantage that may allow them to learn task distributions that smaller models will inevitably fail to learn within the same training setup
Core framing.
Source paper
extracted_from(2026) · Jing Huang · Daniel Wurgaft · Rachit Bansal · Laura Ruis +5
Neighborhood — ranked by edge-count
Papers (1)
paper
Claims (1)
claim
- Core phenomenological argument.
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.
- Hypothesis box in §3.2.
- Distinguishes from undertraining.
- Motivating question.
- Inverse scaling interpretation.
- Selective pressure toward convergence via task generality
- Future direction.
- Bigger models are more likely to converge to a shared representation than smaller modelshypothesis0.813Selective pressure toward convergence via model capacity
- Larger OLMo models achieve both low training loss and high test accuracy, i.e. learn generalizable structurefinding0.804Fig. 5.