Unverified50% confidenceOpinionExact time
On the LongMemEval multi-hop task, increasing the number of retrieved chunks improves recall, but it enters a plateau at 20 chunks, indicating that the bottleneck is not retrieval width but the inherent limitation of vocabulary matching.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/14/2026
First Seen
Valid until: 1/12/2027
Sources
Related Entities
Related Claims
Unverified增加子线程数量不等于增加智力或能力，当数量超过阈值（如20个甚至100个）会出现重复搜索、相互锚定等问题导致效率下降75% similarUnverifiedVector distance and retrieval thresholds are a trade-off between recall and accuracy: the looser the threshold (the larger the value), the more is recalled, but the higher the probability of irrelevant content being mixed in; tightening the threshold may miss answers that could have been reused.72% similarUnverifiedAs the number of constraints grows, certain solvers may face performance bottlenecks.71% similarUnverifiedFor short fragmented notes, insufficient vector information can cause false recall rates to rise significantly, and when the volume of records is insufficient, the association network becomes too sparse.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1030839API
curl https://kongchang.com/api/v1/knowledge/claims/1030839MCP
get_claim(id=1030839)