What is the effect of more generalized NLI training data on NLI Diversity performance?

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• NLI Diversity is limited by the scope of the NLI model's training dataclaim0.857
  Limitation acknowledged in discussion section
• Confidence NLI Diversity achieves state-of-the-art performance on measuring semantic diversityclaim0.815
  Main performance claim of the paper
• What is the role of neutral NLI predictions in measuring semantic diversity?question0.804
  Motivates the creation of Neutral NLI Diversity as an ablation
• Baseline NLI Diversitymethod0.793
  First variant: aggregates argmax NLI class predictions with contradiction=+1, entailment=-1, neutral=0
• NLI Diversitymethod0.782
  Novel metric proposed in this paper using NLI predictions to score semantic diversity of a response set
• Diversity Threshold Generation results in average 137% increase in NLI Diversity compared to standard generationfinding0.775
  Key headline result of the DTG procedure across all conditions
• Neutral NLI predictions may capture lexical rather than semantic diversityhypothesis0.774
  Hypothesis proposed to explain Neutral NLI Diversity's high performance on decTest but low on conTest
• Training on image data should improve LLM performance, and training on language data should improve vision model performancehypothesis0.772
  Implication of PRH for cross-modal training efficiency