Unverified50% confidenceFactExact time
The BM25 score consists of three parts: IDF, term-frequency saturation (k1), and length normalization (b), with the IDF formula being log((N - n + 0.5) / (n + 0.5) + 1).
1
Sources
50%
Confidence
Long-term
Relevance
10/20/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe 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 0.75.72% 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.61% similarUnverifiedOn 194 Yelp text judgments, B1 (0.8B) got 184 correct and B2 (4B) got 192 correct; the average NLLs were 0.09620 and 0.04024, respectively.60% similarUnverifiedScores across 19 models ranged from 0.55 to 1.00, with Qwen 3 235B A22B Instruct ranking first at 1.00.58% similarUnverifiedIn the example, using equal-weight RRF with k=60, chunk B (generic login troubleshooting advice) ranks first, even though chunk A contains the specific fix.57% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1072978API
curl https://kongchang.com/api/v1/knowledge/claims/1072978MCP
get_claim(id=1072978)