Unverified50% confidenceFactExact time
Semantic similarity retrieval measures topic relevance rather than answer entailment; a passage may be topically relevant yet lack the specific facts needed to answer the question, which is the direct cause of inducing unsupported inferences in language models.
1
Sources
50%
Confidence
Long-term
Relevance
10/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedVector retrieval understands semantic similarity rather than literal overlap, which is fundamentally different from traditional keyword matching.79% similarUnverifiedThe study tests the model on two categories of downstream benchmarks: question-answering and semantic text similarity.74% similarUnverifiedDirectional validation is more linguistically meaningful than merely reporting cosine similarity values, because it corresponds to interpretable historical questions.74% similarUnverifiedClustering keywords by semantic similarity is a common misconception, because words that are linguistically similar may span completely different decision stages.71% similarVerifiedLarge language models have a sycophancy characteristic, tending to organize their output according to the inclination of the prompt rather than reflecting factual truth.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1049646API
curl https://kongchang.com/api/v1/knowledge/claims/1049646MCP
get_claim(id=1049646)