Unverified50% confidenceBenchmarkExact time
At a similar flagging rate, a zero-shot decision-model monitor caught only 26% of leaking calls, versus 82% for the linear probe.
1
Sources
50%
Confidence
Long-term
Relevance
10/30/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn the experiments, the task resolution rate was 17% for zero-shot generation, 27% for generic self-correction, 23% for error-only feedback, and 90% for diagnostic counterexample feedback (A-CEGIS).73% similarUnverifiedOn a test subset of 152 completely untouched questions, anchored hybrid retrieval achieved 42.11%, while the planner-guided method reached only 36.84%.73% similarUnverifiedWhen large models answer directly, their pass rate on implicit scoring criteria is only 67%, while their pass rate on explicit criteria reaches 81%.73% similarUnverifiedBenign paraphrases shifted support judgments by only 0%–2.5% under the blind-verifier prompt.72% similarUnverifiedDuring testing, cases emerged where a model claimed 95% confidence in a move but scored 0 points according to the evaluation criteria.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1115384API
curl https://kongchang.com/api/v1/knowledge/claims/1115384MCP
get_claim(id=1115384)