BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Research and Assessment of Occupational Personality Scales Based o
 n Large Language Models - Dr Chanjin Zheng\, East China Normal University
DTSTART:20260331T110000Z
DTEND:20260331T120000Z
UID:TALK245821@talks.cam.ac.uk
CONTACT:Luning Sun
DESCRIPTION:As Large Language Models (LLMs) integrate into professional do
 mains\, understanding their occupational adaptability is critical for huma
 n-AI collaboration. This presentation explores the "occupational personali
 ty" of LLMs and their potential as simulated participants in psychometric 
 research\, utilizing a forced-choice occupational personality scale (MAP).
 \n\nWe 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-p
 laying prompts (e.g.\, simulating managers\, tech innovators\, or financia
 l experts) can effectively align LLM traits with human professional expect
 ations. Ultimately\, this research uncovers the structural characteristics
  of LLM personalities and proposes a novel paradigm for validating psychom
 etric tools using AI subjects.\n
LOCATION:S3.05\, Simon Sainsbury Centre\, Cambridge Judge Business School
END:VEVENT
END:VCALENDAR