Unverified50% confidenceFactExact time
Pairwise comparisons are more reliable than absolute scoring in terms of judgment consistency; Thurstone's Law of Comparative Judgment, proposed in 1927, states that human judgment consistency in relative comparisons is significantly higher than in absolute quantitative assessments.
1
Sources
50%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
Unverified在事实性评估任务上模型评判者准确率仍显著低于人类专家，但在风格、连贯性等主观维度已接近人类评审员间一致性水平69% similarUnverifiedPrecision bias refers to the tendency for people to assign higher credibility to statements containing precise numbers; experiments show that subjects rated the credibility of "41.3%" significantly higher than "approximately 40%".64% similarUnverified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%61% similarUnverified对同一测试用例执行多次调用统计成功比例得到通过率，比二元的通过/失败判断更能反映模型真实表现60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/893228API
curl https://kongchang.com/api/v1/knowledge/claims/893228MCP
get_claim(id=893228)