Unverified50% confidenceFactExact time
Common retrieval-side metrics include Recall@k, MRR (mean reciprocal rank), and context precision.
1
Sources
50%
Confidence
Long-term
Relevance
11/9/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe recall@k metric is highly sensitive to the value of k, the intrinsic dimensionality and clustering structure of the dataset, and whether reranking is used.72% similarUnverifiedMRR (Mean Reciprocal Rank) is the average of Reciprocal Rank over all answerable cases; it only takes the position of the first relevant result and does not care whether the remaining relevant documents were recalled.70% similarUnverifiedrecall@k refers to the proportion of questions for which the top k results contain at least one correct text chunk.68% similarUnverifiedRecall in vector retrieval usually refers to recall@k: of the k results returned, what proportion fall within the true nearest-neighbor set obtained by brute-force exact search.67% similarUnverifiedThe cumulative regret upper bound of standard GP-UCB is parameterized by the RKHS norm bound and the maximum information gain.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1151565API
curl https://kongchang.com/api/v1/knowledge/claims/1151565MCP
get_claim(id=1151565)