Unverified50% confidenceSolutionExact time
Reciprocal Rank Fusion (RRF) is insensitive to score scale; as long as a document consistently ranks high across multiple retrieval results, its final fusion score will improve, making it in practice more robust than manually tuning weights.
1
Sources
50%
Confidence
Long-term
Relevance
10/3/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedWhen the number of knowledge bases is small, fusion methods such as RRF work well, but when the number of knowledge bases grows beyond 10, the default fusion strategy breaks down.72% similarUnverifiedRRF对各路检索的原始分数分布不敏感，相比简单的线性加权在混合检索场景中更加鲁棒69% similarUnverified块划分粒度是多目标优化问题：块越小近似精度越高但元数据开销增大且GPU并行效率降低68% similarUnverifiedCFG guidance strength typically seeks the best balance between 5 and 12; too low deviates from the prompt, while too high produces oversaturation or artifacts.67% similarUnverifiedUsing excessively high CFG values during low-step inference amplifies the correction magnitude at each step, leading to oversaturated colors, distorted contrast, and even artifacts; when using an accelerated LoRA, the CFG value often needs to be reduced from 7.5 to 2–4.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/970551API
curl https://kongchang.com/api/v1/knowledge/claims/970551MCP
get_claim(id=970551)