Unverified50% confidenceBenchmarkExact time
In the end-to-end evaluation, the targeted repetition strategy brought a relative WER reduction of up to 24%.
1
Sources
50%
Confidence
Long-term
Relevance
10/20/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedIn 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% similarUnverifiedModule residual anchoring lowered the hit rate under natural questioning from 28.7% to 22.0% while also reducing the measured behavioral drift, a trade-off of exchanging recall for preservation of non-target behavior.73% similarUnverifiedAnthropic'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%).73% similarUnverified21.2% is a relative reduction rather than an absolute one, meaning the new version eliminates approximately one-fifth of the failures relative to the earlier version's failure rate baseline.73% similarUnverifiedUnder the influence of multi-turn narratives, the models' final judgments shifted by an average of 25 percentage points compared to matched single-turn baselines.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1074677API
curl https://kongchang.com/api/v1/knowledge/claims/1074677MCP
get_claim(id=1074677)