Unverified50% confidenceFactExact time
When the same question is posed in different languages, the documents retrieved by a multilingual dense retriever differ enormously.
1
Sources
50%
Confidence
Long-term
Relevance
10/14/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedWhen documents from all languages are mixed in the same index, relevant documents that should rank near the top for a given language are pushed far down by large numbers of irrelevant documents.73% similarUnverifiedWhen multiple large language models strongly disagree in their annotations of the same document, it often indicates that the codebook rules at that point are ambiguous, equivocal, or insufficiently covered.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1023570API
curl https://kongchang.com/api/v1/knowledge/claims/1023570MCP
get_claim(id=1023570)