Unverified50% confidenceBenchmarkExact time
The audit results show that automatic labels agree with human consensus on 90.3% of claims, with a Cohen's Kappa coefficient of 0.87.
1
Sources
50%
Confidence
Long-term
Relevance
9/23/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe human baseline accuracy is 90.8%.70% similarUnverifiedResearch shows that the agreement rate between LLM judges and human scores is approximately 80%, approaching but not yet surpassing the level of human inter-annotator agreement (approximately 81%).69% similarUnverifiedUnder the leave-one-author-out cross-validation setting, the strongest model achieved an accuracy of 81.42%.66% similarUnverified研究表明经过良好校准的LLM裁判与人工标注的一致性可达80%以上66% similarUnverifiedA study published in Nature in 2020 found that Cohen's Kappa coefficient for different reviewers' scores on the same paper is typically less than 0.3.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/942888API
curl https://kongchang.com/api/v1/knowledge/claims/942888MCP
get_claim(id=942888)