method
active
method:human-diversity-annotation-likert-scaleHuman Diversity Annotation (Likert Scale)
Annotators score diversity of response sets 1-5 with half-point increments; used as ground truth correlation target
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.
- 1-to-5 response scale used throughout psychometric scoring
- The quality of spatial dimensions that feel comfortable and nurturing to human beings.
- Confidence NLI Diversity achieves ρ=0.64 correlation with human diversity judgments on conTestfinding0.735Highest human correlation for semantic diversity metric
- Three independent human annotators labeling 100 responses to validate Llama Guard 3 safety classifications
- Diversity metric computed as 1 minus mean pairwise cosine similarity of response embeddings, using OpenAI's text-embedding-3-small
- The breadth of distinct outputs an LLM can produce, which is reduced by mode collapse after alignment training
- Research program studying intelligence at multiple scales and substrates; proposed as relevant to implications of mnemonic improvisation.