Unverified50% confidenceBenchmarkExact time
On the nDCG@10 ranking metric, SAFE-QE shows no statistically significant difference from generative expansion and corpus-guided expansion.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedSAFE-QE models the selection of expansion terms as a constrained coverage maximization problem over the pseudo-relevant set, with the objective of retaining a set of expansion terms that is sufficiently broad, consistent, and stable under resampling.74% similarUnverifiedSAFE-QE is a training-free and retriever-agnostic query expansion method, whose full name is Subsequence-Association Filtered, breadth-aware Query Expansion.61% similarUnverified量化主流格式包括GPTQ、AWQ、GGUF等，INT4量化相比FP16通常导致模型在复杂推理、数学和代码任务上出现明显退化57% similarUnverifiedThe ontology layer has advantages over RAG in handling precise numerical queries, cross-table association analysis, and ensuring metric consistency, because it provides deterministic business rules rather than probabilistic text similarity matching.57% similarUnverified在一对多关系中用错JOIN键会产生行数膨胀，使SUM聚合结果成倍增长，而SQL不会抛出任何异常56% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1002089API
curl https://kongchang.com/api/v1/knowledge/claims/1002089MCP
get_claim(id=1002089)