hypothesis
active
hypothesis:larger-numbers-of-entailment-predictions-indicate-lack-of-diversity-larger-numbers-of-contradiction-predictions-indicate-higher-diversityLarger numbers of entailment predictions indicate lack of diversity; larger numbers of contradiction predictions indicate higher diversity
Design hypothesis for NLI scoring weights in Baseline NLI Diversity
Source paper
extracted_from(2022) · Katherine Stasaski · Marti A. Hearst
Neighborhood — ranked by edge-count
Papers (1)
paper
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.
- Ablation result confirming that entailment predictions indicate lack of diversity
- For reasoning faithfulness, larger models may behave worse than smaller ones because they can predict answers without CoT.hypothesis0.792Motivates §3.
- Inverse scaling interpretation.
- # Contradiction is positively correlated with diversity (ρ=0.26 decTest, ρ=0.46 conTest)finding0.759Ablation result confirming that contradiction predictions indicate diversity
- Bigger models are more likely to converge to a shared representation than smaller modelshypothesis0.759Selective pressure toward convergence via model capacity
- The contradiction relation is more useful than the neutral relation for measuring semantic diversityclaim0.758Key finding from ablation study on NLI prediction categories
- Interpretation of steering asymmetry.
- Practical implication.