question
active
question:if-a-model-sees-too-many-observations-of-the-same-task-does-it-perhaps-undergo-overfitting-and-does-scaling-help-avoid-this-via-double-descentif a model sees too many observations of the same task, does it perhaps undergo overfitting, and does scaling help avoid this via double descent?
Future work for frequent tasks.
Source paper
extracted_from(2026) · Jing Huang · Daniel Wurgaft · Rachit Bansal · Laura Ruis +5
Neighborhood — ranked by edge-count
Papers (1)
paper
- Why Larger Models Learn More: Effects of Capacity, Interference, and Rare-Task Retentionassociated_withmentions
Claims (1)
claim
- Discussion and App. A.
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.
- Practical implication.
- Fig. 23.
- Implication of PRH for AI fairness and bias
- Implication of PRH: larger models should amplify bias less and hallucinate less if they better model reality
- Selective pressure toward convergence via task generality
- Inverse scaling interpretation.
- Practical implication.
- Hypothesis box in §3.2.