Unverified50% confidenceBenchmarkExact time
In university-level proof grading, even with the experts' grading rubric in hand, 5 of 7 evaluators still passed 38.0% to 45.7% of proofs that experts judged as failures, while falsely failing only 5.0% to 12.3% of correct proofs.
1
Sources
50%
Confidence
Long-term
Relevance
10/14/2026
First Seen
Sources
Related Entities
Related Claims
Unverified研究表明人类评估者在判断LLM输出的事实准确性时，正确率往往只有50%-70%76% similarUnverifiedA single "trusted source" prompt caused 7 out of 8 tested models to reverse between 45% and 88% of their correct answers.74% similarUnverifiedIn the multiple testing problem, if each independent test produces a false positive with a 5% probability at the 5% significance level, then after 20 independent attempts the probability of at least one false positive is about 64%.73% similarUnverifiedA detection rate of 73.43% means that approximately one in four core errors still goes uncaught, indicating that automated review cannot yet fully replace the judgment of human experts.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1026031API
curl https://kongchang.com/api/v1/knowledge/claims/1026031MCP
get_claim(id=1026031)