Unverified50% confidenceDecision RuleExact time
LLMs are naturally inclined to give answers even when faced with incomplete data; the system prompt must explicitly force an UNKNOWN classification to be output when evidence is insufficient, guiding the human owner to take over.
1
Sources
50%
Confidence
Long-term
Relevance
10/15/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedLLMs perform reliably in high-recall screening tasks such as title-abstract screening and full-text screening, but show a marked decline in evidence extraction tasks and still require human leadership.72% similarUnverifiedThe LLM judge mechanism verifies the presence of information rather than its absence, so there is no clear anchor to trigger a check for omissions.72% similarUnverifiedWhen documents are processed by an LLM as equally weighted factual sources, their staleness gets amplified into concrete incorrect answers.71% similarUnverifiedAbsence verification requires the model to actively infer which important information that should have appeared in the source material was omitted, necessitating the prior construction of a complete mental model of what ought to be present, which is far more difficult for LLMs.71% similarUnverifiedLLMs have a strong tendency toward error tolerance and completion, and when faced with misaligned table data they typically do not report errors but instead produce seemingly reasonable inferences based on the erroneous data.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1035278API
curl https://kongchang.com/api/v1/knowledge/claims/1035278MCP
get_claim(id=1035278)