concept
active
concept:multi-response-diversity

Multi-Response Diversity

Diversity measured over a set of m responses for a single conversation, as opposed to test set diversity

Neighborhood — ranked by edge-count

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

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

  • A response containing multiple distinct attempts to answer the prompt, used as primary metric for ESR
  • Target minimum diversity level (e.g., 10 contradictions) that DTG iterates toward
  • Output Diversityconcept0.770
    The breadth of distinct outputs an LLM can produce, which is reduced by mode collapse after alignment training
  • Lexical Diversityconcept0.760
    Contrasted with semantic diversity; measured by n-gram overlap and distinct-n
  • Responsivenessconcept0.747
    Requirement that answers to questions be responsive as well as truthful; requires knowing that questioner will know the answer after receiving it.
  • Gold standard value (e.g., nucleus sampling p-value) used as ground truth for evaluating diversity metrics
  • Stress Responseconcept0.744
  • A prompting baseline that elicits N responses across N sequential conversation turns