Unverified50% confidenceBenchmarkExact time
Benign paraphrases shifted support judgments by only 0%–2.5% under the blind-verifier prompt.
1
Sources
50%
Confidence
Long-term
Relevance
10/2/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedCorrupted reasoning chains shifted support judgments by 10%–22% under the blind-verifier prompt.75% similarUnverifiedAccording to Jev's official blog, its 0% hallucination rate does not come from empirical testing; what is actually guaranteed is only that the returned answer conforms to the permitted schema.73% similarUnverifiedThe study found that the faithfulness score for counterfactual inputs was only 0.05 points lower than for factual inputs (on a 1–5 scale), a difference that is almost negligible.71% similarUnverifiedIn scenarios with extreme class imbalance (such as fraud detection), looking solely at accuracy as an evaluation metric is completely meaningless.70% similarUnverifiedAdding a "Do not guess" instruction to the prompt can reduce the proportion of fabricated false claims by a model from 71% to 20%.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/966688API
curl https://kongchang.com/api/v1/knowledge/claims/966688MCP
get_claim(id=966688)