concept
active
concept:multi-response-diversityMulti-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
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.
- 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
- The breadth of distinct outputs an LLM can produce, which is reduced by mode collapse after alignment training
- Contrasted with semantic diversity; measured by n-gram overlap and distinct-n
- 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
- A prompting baseline that elicits N responses across N sequential conversation turns