Verified80% confidenceFactTime unknown
BM25 (Best Matching 25) is a probabilistic ranking algorithm proposed by Stephen Robertson and others in the 1990s, scoring relevance based on three factors: term frequency, inverse document frequency, and document length normalization.
6
Sources
80%
Confidence
Long-term
Relevance
6/1/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedUnder an 18k character budget, anchored hybrid retrieval achieved 36.18% accuracy, BM25 achieved 35.98%, while the best direct planner-guided method reached only 34.19%.63% similarUnverifiedVector retrieval returns cosine similarity or distance scores, while BM25 returns term-frequency-based scores; the two have different units, so raw scores cannot be directly added or compared.62% similarVerifiedThe core mechanism of BM25 is based on three factors: term frequency (TF), inverse document frequency (IDF), and document length normalization, with parameter k1 typically set between 1.2 and 2.0 and b typically set at 0.75.61% similarUnverifiedThe weights of a Q4-quantized model are roughly 30% the size of BF16 precision, a ratio that accounts for quantization scaling factors and redundant storage overhead.60% similarUnverifiedUsing a 4B model to rerank the candidate shortlist filtered by BM25 outperformed BM25 alone (+0.047, confidence interval [0.020, 0.073]), even though the 4B reranker itself did not pass qualification.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/26802API
curl https://kongchang.com/api/v1/knowledge/claims/26802MCP
get_claim(id=26802)