Scaling Law in LLM Simulated Personality: More Detailed and Realistic Persona Profile Is All You Need

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Bai, Yuqi, Huang, Tianyu, Sun, Kun, Chen, Yuting
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914091228987392
author Bai, Yuqi
Huang, Tianyu
Sun, Kun
Chen, Yuting
author_facet Bai, Yuqi
Huang, Tianyu
Sun, Kun
Chen, Yuting
contents This research focuses on using large language models (LLMs) to simulate social experiments, exploring their ability to emulate human personality in virtual persona role-playing. The research develops an end-to-end evaluation framework, including individual-level analysis of stability and identifiability, as well as population-level analysis called progressive personality curves to examine the veracity and consistency of LLMs in simulating human personality. Methodologically, this research proposes important modifications to traditional psychometric approaches (CFA and construct validity) which are unable to capture improvement trends in LLMs at their current low-level simulation, potentially leading to remature rejection or methodological misalignment. The main contributions of this research are: proposing a systematic framework for LLM virtual personality evaluation; empirically demonstrating the critical role of persona detail in personality simulation quality; and identifying marginal utility effects of persona profiles, especially a Scaling Law in LLM personality simulation, offering operational evaluation metrics and a theoretical foundation for applying large language models in social science experiments.
format Preprint
id arxiv_https___arxiv_org_abs_2510_11734
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Scaling Law in LLM Simulated Personality: More Detailed and Realistic Persona Profile Is All You Need
Bai, Yuqi
Huang, Tianyu
Sun, Kun
Chen, Yuting
Computers and Society
Artificial Intelligence
Computation and Language
This research focuses on using large language models (LLMs) to simulate social experiments, exploring their ability to emulate human personality in virtual persona role-playing. The research develops an end-to-end evaluation framework, including individual-level analysis of stability and identifiability, as well as population-level analysis called progressive personality curves to examine the veracity and consistency of LLMs in simulating human personality. Methodologically, this research proposes important modifications to traditional psychometric approaches (CFA and construct validity) which are unable to capture improvement trends in LLMs at their current low-level simulation, potentially leading to remature rejection or methodological misalignment. The main contributions of this research are: proposing a systematic framework for LLM virtual personality evaluation; empirically demonstrating the critical role of persona detail in personality simulation quality; and identifying marginal utility effects of persona profiles, especially a Scaling Law in LLM personality simulation, offering operational evaluation metrics and a theoretical foundation for applying large language models in social science experiments.
title Scaling Law in LLM Simulated Personality: More Detailed and Realistic Persona Profile Is All You Need
topic Computers and Society
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2510.11734