Unverified50% confidenceCautionExact time
TF-IDF/BM25 retrieval fails when there is vocabulary drift (the same concept expressed differently), which is a known limitation of the current approach and needs embedding models or query rewriting to compensate.
1
Sources
50%
Confidence
Long-term
Relevance
10/14/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe routing problem stems from the limitations of lexical search itself: when the user message is a vague instruction, the question contains almost no usable retrieval signal, and no matter how strong BM25 is, it has nothing to work with.70% similarUnverifiedWhen the retrieval context does not contain the answer, many language models fill the gap with plausible-sounding content, which is exactly the hallucination users notice; fixes include instructing the model to answer only from the provided context, giving it a clear way to opt out, requiring a citation for every claim, setting a retrieval score threshold, and logging rejected questions.62% similarUnverified检索策略的效果高度依赖数据特征——在FAQ上BM25可能打败向量检索，在语义模糊的查询上则相反。62% similarUnverifiedA Catch-22 loop refers to a situation where a system requires the user to provide information A in order to resolve problem B, while problem B is precisely the reason the user cannot obtain information A.62% similarUnverifiedDynamically adding or removing tool definitions in each request will cause the prefix hash to change, invalidating the cache.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1030838API
curl https://kongchang.com/api/v1/knowledge/claims/1030838MCP
get_claim(id=1030838)