Guardado en:
Detalles Bibliográficos
Autores principales: Huang, Yin Jou, Hadfi, Rafik
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2504.08399
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913848514052096
author Huang, Yin Jou
Hadfi, Rafik
author_facet Huang, Yin Jou
Hadfi, Rafik
contents Self-report questionnaires have long been used to assess LLM personality traits, yet they fail to capture behavioral nuances due to biases and meta-knowledge contamination. This paper proposes a novel multi-observer framework for personality trait assessments in LLM agents that draws on informant-report methods in psychology. Instead of relying on self-assessments, we employ multiple observer agents. Each observer is configured with a specific relational context (e.g., family member, friend, or coworker) and engages the subject LLM in dialogue before evaluating its behavior across the Big Five dimensions. We show that these observer-report ratings align more closely with human judgments than traditional self-reports and reveal systematic biases in LLM self-assessments. We also found that aggregating responses from 5 to 7 observers reduces systematic biases and achieves optimal reliability. Our results highlight the role of relationship context in perceiving personality and demonstrate that a multi-observer paradigm offers a more reliable, context-sensitive approach to evaluating LLM personality traits.
format Preprint
id arxiv_https___arxiv_org_abs_2504_08399
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Beyond Self-Reports: Multi-Observer Agents for Personality Assessment in Large Language Models
Huang, Yin Jou
Hadfi, Rafik
Computation and Language
Artificial Intelligence
Self-report questionnaires have long been used to assess LLM personality traits, yet they fail to capture behavioral nuances due to biases and meta-knowledge contamination. This paper proposes a novel multi-observer framework for personality trait assessments in LLM agents that draws on informant-report methods in psychology. Instead of relying on self-assessments, we employ multiple observer agents. Each observer is configured with a specific relational context (e.g., family member, friend, or coworker) and engages the subject LLM in dialogue before evaluating its behavior across the Big Five dimensions. We show that these observer-report ratings align more closely with human judgments than traditional self-reports and reveal systematic biases in LLM self-assessments. We also found that aggregating responses from 5 to 7 observers reduces systematic biases and achieves optimal reliability. Our results highlight the role of relationship context in perceiving personality and demonstrate that a multi-observer paradigm offers a more reliable, context-sensitive approach to evaluating LLM personality traits.
title Beyond Self-Reports: Multi-Observer Agents for Personality Assessment in Large Language Models
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2504.08399