question
active
question:what-is-it-about-the-data-that-only-a-larger-model-can-learn-such-that-the-smaller-model-cannot-even-after-observing-infinite-datawhat is it about the data that only a larger model can learn, such that the smaller model cannot, even after observing infinite data?
Motivating question.
Source paper
extracted_from(2026) · Jing Huang · Daniel Wurgaft · Rachit Bansal · Laura Ruis +5
Neighborhood — ranked by edge-count
Papers (1)
paper
Findings (1)
finding
- Fig. 2 verification.
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.
- Core framing.
- Distinguishes from undertraining.
- Hypothesis box in §3.2.
- Future direction.
- Inverse scaling interpretation.
- Core goal statement.
- Key limitation of the PRH for non-bijective observations
- Clarifies what unsupervised learning does.