Unverified50% confidenceFactExact time
MRR (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.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedRRF (Reciprocal Rank Fusion) uses only the ranking position information from each retrieval path (formula RRF(d)=Σ1/(k+rank_i(d)), where k is typically set to 60), is insensitive to score distribution, and bypasses the cross-modal score alignment problem59% similarUnverifiedNeither Recall@k nor Reciprocal Rank@k measures whether the final answer is correct, safe, or grounded; both only answer questions at the retrieval level.57% similarVerifiedRRF does not require normalization of raw scores from different retrievers and relies only on rank information, but when multiple retrievers systematically make the same type of error, RRF only amplifies the mistakes56% similarUnverifiedReranking technology first uses coarse retrieval to recall a large number of candidate segments, then uses a fine-ranking model to re-score them, keeping only the most relevant content to feed into the model.53% similarUnverified召回加重排（Recall + Rerank）先用 embedding 或关键词检索召回 Top 10 候选，再交给大模型做最终裁决，与RAG思路一致51% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1005607API
curl https://kongchang.com/api/v1/knowledge/claims/1005607MCP
get_claim(id=1005607)