Unverified50% confidenceBenchmarkExact time
On real-world queries, RATED achieves a 52.2% relative MRR improvement over ToolLLM's API retriever.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/12/2026
First Seen
Valid until: 1/10/2027
Sources
Related Entities
Related Claims
UnverifiedPiPMRE achieves an average improvement of 5.6 percentage points in recall over the previous state-of-the-art methods on two public datasets.60% similarUnverifiedThe MTP speculative decoding technology integrated in Strata has a higher hit rate than ordinary inference frameworks, delivering an overall speedup of 1.6x to 1.8x.60% similarUnverifiedWhen retaining more than 50% of dimensions, the retrieval accuracy loss of PCA is typically within 1-5%, which is comparable to MRL.59% similarUnverified顶级提示词用户与普通用户在相同模型上获得的输出质量差异可能高达数倍59% similarUnverifiedvLLM's measured throughput can be improved by 2–4× compared to a naive implementation.58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1001935API
curl https://kongchang.com/api/v1/knowledge/claims/1001935MCP
get_claim(id=1001935)