Unverified50% confidenceFactExact time
Whether a page can be cited by RAG involves at least two thresholds: whether it is included in the retrieval index and whether its semantic similarity is high enough, as well as whether, once recalled, it is judged to be a high-quality, trustworthy source.
1
Sources
50%
Confidence
Long-term
Relevance
9/27/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedRetrieval-Augmented Generation (RAG) anchors facts by incorporating real-time web search with cited sources, but its effectiveness is influenced by factors such as search result quality, document parsing accuracy, and the model's comprehension capability.68% similarUnverified不同的用户提问表述会生成不同的向量，与文档内容的语义距离也会有所差异，影响RAG检索效果66% similarUnverifiedMainstream RAG evaluation frameworks include RAGAS, TruLens, and DeepEval, which typically score across two dimensions—retrieval quality and generation quality—but lack built-in support for specialized requirements such as exact identifier matching and rule clause completeness66% similarUnverifiedWhen comparing search performance horizontally across platforms, creators need to account for differences in index coverage across platforms to avoid misjudgments caused by direct equal comparison of data.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/953754API
curl https://kongchang.com/api/v1/knowledge/claims/953754MCP
get_claim(id=953754)