University of Cambridge > Talks.cam > Cambridge Psychometrics Centre Seminars > Research and Assessment of Occupational Personality Scales Based on Large Language Models

Research and Assessment of Occupational Personality Scales Based on Large Language Models

Download to your calendar using vCal

If you have a question about this talk, please contact Luning Sun .

As Large Language Models (LLMs) integrate into professional domains, understanding their occupational adaptability is critical for human-AI collaboration. This presentation explores the “occupational personality” of LLMs and their potential as simulated participants in psychometric research, utilizing a forced-choice occupational personality scale (MAP).

We first evaluate six mainstream LLMs on the MAP scale, demonstrating excellent reliability, including traditional measurement reliability and LLM -related reliability. Next, we apply the scale to evaluate how role-playing prompts (e.g., simulating managers, tech innovators, or financial experts) can effectively align LLM traits with human professional expectations. Ultimately, this research uncovers the structural characteristics of LLM personalities and proposes a novel paradigm for validating psychometric tools using AI subjects.

This talk is part of the Cambridge Psychometrics Centre Seminars series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

Β© 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity