Realistic threat perception drives intergroup conflict: A causal, dynamic analysis using generative-agent simulations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Abdurahman, Suhaib, Karimi-Malekabadi, Farzan, Yu, Chenxiao, Kteily, Nour S., Dehghani, Morteza
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917156630822912
author Abdurahman, Suhaib
Karimi-Malekabadi, Farzan
Yu, Chenxiao
Kteily, Nour S.
Dehghani, Morteza
author_facet Abdurahman, Suhaib
Karimi-Malekabadi, Farzan
Yu, Chenxiao
Kteily, Nour S.
Dehghani, Morteza
contents Human conflict is often attributed to threats against material conditions and symbolic values, yet it remains unclear how they interact and which dominates. Progress is limited by weak causal control, ethical constraints, and scarce temporal data. We address these barriers using simulations of large language model (LLM)-driven agents in virtual societies, independently varying realistic and symbolic threat while tracking actions, language, and attitudes. Representational analyses show that the underlying LLM encodes realistic threat, symbolic threat, and hostility as distinct internal states, that our manipulations map onto them, and that steering these states causally shifts behavior. Our simulations provide a causal account of threat-driven conflict over time: realistic threat directly increases hostility, whereas symbolic threat effects are weaker, fully mediated by ingroup bias, and increase hostility only when realistic threat is absent. Non-hostile intergroup contact buffers escalation, and structural asymmetries concentrate hostility among majority groups.
format Preprint
id arxiv_https___arxiv_org_abs_2512_17066
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Realistic threat perception drives intergroup conflict: A causal, dynamic analysis using generative-agent simulations
Abdurahman, Suhaib
Karimi-Malekabadi, Farzan
Yu, Chenxiao
Kteily, Nour S.
Dehghani, Morteza
Artificial Intelligence
Human conflict is often attributed to threats against material conditions and symbolic values, yet it remains unclear how they interact and which dominates. Progress is limited by weak causal control, ethical constraints, and scarce temporal data. We address these barriers using simulations of large language model (LLM)-driven agents in virtual societies, independently varying realistic and symbolic threat while tracking actions, language, and attitudes. Representational analyses show that the underlying LLM encodes realistic threat, symbolic threat, and hostility as distinct internal states, that our manipulations map onto them, and that steering these states causally shifts behavior. Our simulations provide a causal account of threat-driven conflict over time: realistic threat directly increases hostility, whereas symbolic threat effects are weaker, fully mediated by ingroup bias, and increase hostility only when realistic threat is absent. Non-hostile intergroup contact buffers escalation, and structural asymmetries concentrate hostility among majority groups.
title Realistic threat perception drives intergroup conflict: A causal, dynamic analysis using generative-agent simulations
topic Artificial Intelligence
url https://arxiv.org/abs/2512.17066