method
active
method:semantic-diversity-scoreSemantic Diversity Score
Diversity metric computed as 1 minus mean pairwise cosine similarity of response embeddings, using OpenAI's text-embedding-3-small
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.
- Core concept measured by NLI Diversity — diversity of meaning across a set of dialogue responses
- Contrasted with semantic diversity; measured by n-gram overlap and distinct-n
- Confidence NLI Diversity achieves state-of-the-art performance on measuring semantic diversityclaim0.781Main performance claim of the paper
- The breadth of distinct outputs an LLM can produce, which is reduced by mode collapse after alignment training
- Motivates the creation of Neutral NLI Diversity as an ablation
- Meaning that arises from relations within the graphical system, not inherent in elements.
- Target minimum diversity level (e.g., 10 contradictions) that DTG iterates toward
- The contradiction relation is more useful than the neutral relation for measuring semantic diversityclaim0.739Key finding from ablation study on NLI prediction categories