@inproceedings{huang-hadfi-2025-beyond,
title = "Beyond Self-Reports: Multi-Observer Agents for Personality Assessment in Large Language Models",
author = "Huang, Yin Jou and
Hadfi, Rafik",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-emnlp.1150/",
doi = "10.18653/v1/2025.findings-emnlp.1150",
pages = "21086--21101",
ISBN = "979-8-89176-335-7",
abstract = "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 LLM agents, each of which is configured with a specific relationship (e.g., family member, friend, or coworker). The observer agents interact with the subject LLM agent before assessing its Big Five personality traits. We show that observer-report ratings align more closely with human judgments than traditional self-reports and reveal systematic biases in LLM self-assessments. Further analysis shows that aggregating ratings of multiple observers provides more reliable results, reflecting a wisdom of the crowd effect up to 5 to 7 observers."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-hadfi-2025-beyond">
<titleInfo>
<title>Beyond Self-Reports: Multi-Observer Agents for Personality Assessment in Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yin</namePart>
<namePart type="given">Jou</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rafik</namePart>
<namePart type="family">Hadfi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-335-7</identifier>
</relatedItem>
<abstract>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 LLM agents, each of which is configured with a specific relationship (e.g., family member, friend, or coworker). The observer agents interact with the subject LLM agent before assessing its Big Five personality traits. We show that observer-report ratings align more closely with human judgments than traditional self-reports and reveal systematic biases in LLM self-assessments. Further analysis shows that aggregating ratings of multiple observers provides more reliable results, reflecting a wisdom of the crowd effect up to 5 to 7 observers.</abstract>
<identifier type="citekey">huang-hadfi-2025-beyond</identifier>
<identifier type="doi">10.18653/v1/2025.findings-emnlp.1150</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.1150/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>21086</start>
<end>21101</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Beyond Self-Reports: Multi-Observer Agents for Personality Assessment in Large Language Models
%A Huang, Yin Jou
%A Hadfi, Rafik
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F huang-hadfi-2025-beyond
%X 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 LLM agents, each of which is configured with a specific relationship (e.g., family member, friend, or coworker). The observer agents interact with the subject LLM agent before assessing its Big Five personality traits. We show that observer-report ratings align more closely with human judgments than traditional self-reports and reveal systematic biases in LLM self-assessments. Further analysis shows that aggregating ratings of multiple observers provides more reliable results, reflecting a wisdom of the crowd effect up to 5 to 7 observers.
%R 10.18653/v1/2025.findings-emnlp.1150
%U https://aclanthology.org/2025.findings-emnlp.1150/
%U https://doi.org/10.18653/v1/2025.findings-emnlp.1150
%P 21086-21101
Markdown (Informal)
[Beyond Self-Reports: Multi-Observer Agents for Personality Assessment in Large Language Models](https://aclanthology.org/2025.findings-emnlp.1150/) (Huang & Hadfi, Findings 2025)
ACL