SEP 9, 2026 · PREPRINT
Strangers to Themselves: What Language Models Say About Themselves Is Generic
arXiv
Exploratory computational study testing self-knowledge in language models using novel methodology, with clear quantitative results but limited scope, no peer review, and no direct clinical or practice guidance.
Reported
Direct self-report correlationr = +0.04
Self-report with item informationr = +0.24
Generic AI agent prediction accur…r = +0.28