Unverified50% confidenceFactExact time
Unlike humans, LLMs' acceptance judgments of generic statements are not influenced by 'strikingness'.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/21/2026
First Seen
Valid until: 1/19/2027
Sources
Related Entities
Related Claims
UnverifiedA correlation of 0.69 indicates that LLM judgments are strongly correlated with but not fully equivalent to human judgments; LLM judges can serve as large-scale screening tools, but human judgment remains irreplaceable in high-stakes decision-making scenarios.80% similarUnverifiedLLM evaluation is more objective than human evaluation, as it can score candidates consistently within a unified evaluation framework, avoiding the unfairness caused by cognitive biases such as fatigue, mood, and the primacy effect in human interviewers.76% similarUnverifiedIn LLMs, the influence of human-like factors such as commonness, distinctiveness and characteristicness is transmitted to model ratings indirectly through 'factual truth' judgments.76% similarUnverifiedPsycholinguistic research shows that human judgments of generic statements are also influenced by 'strikingness' (whether the property is striking).74% similarUnverifiedHuman acceptance of generic statements depends not only on the frequency with which a property occurs in a category but is also influenced by factors such as distinctiveness and characteristicness.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1079535API
curl https://kongchang.com/api/v1/knowledge/claims/1079535MCP
get_claim(id=1079535)