Unverified50% confidenceOpinionExact time
When the knowledge base cannot answer a query, vector retrieval still returns semantically "seemingly relevant" fragments, so the large model may fabricate an answer as a result.
1
Sources
50%
Confidence
Long-term
Relevance
10/28/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe answer quality of the knowledge base approach depends on the materials themselves and the retrieval results; when nothing is retrieved or the materials are vague, the model can only fall back on general common sense.80% similarUnverifiedGlobal queries can answer inductive questions requiring a macro perspective (such as the main themes across an entire document set), a scenario that pure vector retrieval is almost incapable of handling.76% similarUnverifiedVector search can retrieve text chunks with high similarity scores, but cannot explain the reasoning logic behind answers, nor structurally connect facts scattered across different documents.75% similarUnverifiedSemantic caching bypasses the model call entirely when a new query is sufficiently similar to an already-answered query, but carries the trade-off of returning incorrect answers to subtly different questions.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1106470API
curl https://kongchang.com/api/v1/knowledge/claims/1106470MCP
get_claim(id=1106470)