Unverified50% confidenceBenchmarkExact time
Anthropic's experiments showed that adding a reranker on top of contextual retrieval brought the reduction in top-20 retrieval failure rate to 67% (from 5.7% to 1.9%).
1
Sources
50%
Confidence
Long-term
Relevance
10/19/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAnthropic's experiments showed that combining embedding with BM25 and adding context to chunks reduced the top-20 retrieval failure rate by 49% (from 5.7% to 2.9%).79% similarUnverifiedIn Anthropic's tests, the failure rate of Naive RAG (the correct text chunk not in the top 20) was 5.7%, dropping to 3.7% with contextual embeddings, 2.9% with contextual BM25, and 1.9% with reranking added.75% similarVerifiedIn long-chain tasks, if each step has an error rate of approximately 5%, the overall success rate may drop to below 36% after 20 steps.74% similarUnverifiedIn the experiment, after prompts exceeded 50, the human interception rate dropped sharply from 17% to 5%, reflecting the phenomenon of approval fatigue.74% similarUnverifiedOnline A/B testing showed a 5% decrease in skip rate.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1065183API
curl https://kongchang.com/api/v1/knowledge/claims/1065183MCP
get_claim(id=1065183)