🧪 Test?View on arXiv
Tracing Psychometric Inference in Large Language Models
Not provided in the content
psychometricslanguage modelsbehavioral analysis
2611.12937
Builder Relevance
17h ago70%
Abstract
This paper investigates whether large language models internally represent psychological constructs or merely generate outputs that mimic psychometric structures.
Reality Card
Core Claim
Larger variants of language models exhibit internal geometric alignment with human psychological constructs, while base variants do not show this alignment.
Method / Result
The correlation between geometry strength and behavioral amplification was found to be r = 0.68, p = 0.008.
Limitations
The study does not establish that the measured directions mediate the cross-persona answers, which raises questions about the reproducibility of the findings.
Paper to code
Verified implementation resources so builders can test the paper’s claims instead of stopping at the abstract.
No verified implementation link has been attached yet. AIBuzzHub will keep this panel separate from unverified search results.