Reproduce “LLMs Aren't Human: A Critical Perspective on LLM Personality” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Kim Zierahn, Cristina Cachero, Anna Korhonen, Nuria Oliver

The authors review whether human personality tests establish that large language models have human-like traits. They assess the tests against six criteria, including stability over time, consistency across situations, and prediction of behavior, drawing on mixed evidence rather than new experiments. They conclude that none of the six criteria is sufficiently met, so test scores do not prove human-like personality.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.