Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Huang, Muhua, Zhang, Xijuan, Soto, Christopher, Evans, James
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2410.19238
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912707400171520
author Huang, Muhua
Zhang, Xijuan
Soto, Christopher
Evans, James
author_facet Huang, Muhua
Zhang, Xijuan
Soto, Christopher
Evans, James
contents We introduce a methodology for assigning quantifiable and psychometrically validated personalities to AI-Agents using the Big Five framework. Across three studies, we evaluate its feasibility and limitations. In Study 1, we show that large language models (LLMs) capture semantic similarities among Big Five measures, providing a basis for personality assignment. In Study 2, we create AI-Agents using prompts designed based on the Big Five Inventory-2 (BFI-2) in different format, and find that AI-Agents powered by new models align more closely with human responses on the Mini-Markers test, although the finer pattern of results (e.g., factor loading patterns) were sometimes inconsistent. In Study 3, we validate our AI-Agents on risk-taking and moral dilemma vignettes, finding that models prompted with the BFI-2-Expanded format most closely reproduce human personality-decision associations, while safety-aligned models generally inflate 'moral' ratings. Overall, our results show that AI-Agents align with humans in correlations between input Big Five traits and output responses and may serve as useful tools for preliminary research. Nevertheless, discrepancies in finer response patterns indicate that AI-Agents cannot (yet) fully substitute for human participants in precision or high-stakes projects.
format Preprint
id arxiv_https___arxiv_org_abs_2410_19238
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Designing AI-Agents with Personalities: A Psychometric Approach
Huang, Muhua
Zhang, Xijuan
Soto, Christopher
Evans, James
Artificial Intelligence
Computers and Society
We introduce a methodology for assigning quantifiable and psychometrically validated personalities to AI-Agents using the Big Five framework. Across three studies, we evaluate its feasibility and limitations. In Study 1, we show that large language models (LLMs) capture semantic similarities among Big Five measures, providing a basis for personality assignment. In Study 2, we create AI-Agents using prompts designed based on the Big Five Inventory-2 (BFI-2) in different format, and find that AI-Agents powered by new models align more closely with human responses on the Mini-Markers test, although the finer pattern of results (e.g., factor loading patterns) were sometimes inconsistent. In Study 3, we validate our AI-Agents on risk-taking and moral dilemma vignettes, finding that models prompted with the BFI-2-Expanded format most closely reproduce human personality-decision associations, while safety-aligned models generally inflate 'moral' ratings. Overall, our results show that AI-Agents align with humans in correlations between input Big Five traits and output responses and may serve as useful tools for preliminary research. Nevertheless, discrepancies in finer response patterns indicate that AI-Agents cannot (yet) fully substitute for human participants in precision or high-stakes projects.
title Designing AI-Agents with Personalities: A Psychometric Approach
topic Artificial Intelligence
Computers and Society
url https://arxiv.org/abs/2410.19238