Truth or Tribe: How In-group Favoritism Prioritize Facts in Persona Agents

TL;DR

This paper investigates in-group favoritism in persona agents, revealing its persistence in misinformation contexts and proposing three strategies to mitigate its effects.

Contribution

It introduces a novel simulation framework to study in-group bias in persona agents and evaluates interventions to reduce this bias.

Findings

Persona agents favor in-group members, accepting false info from them more than from out-group members.

In-group favoritism persists in ambiguous truth scenarios and increases with cognitive complexity.

Three mitigation strategies effectively reduce in-group bias in persona agents.

Abstract

In-group favoritism refers to the phenomena of favoring members of one's in-group over out-group members and is widely observed in numerous social cooperative behaviors. Recently, in-group favoritism biases have also been identified in generative language models. However, whether the in-group favoritism exists when persona agents are faced with contradicting information (e.g., misinformation), and how to mitigate the adverse effects of in-group favoritism biases in persona agents have been understudied. To address these problems, we propose a Truth or Tribe simulation framework to study the agent cooperation within the spread of contradicting information through a triadic interaction paradigm, and conduct controlled trials to evaluate the primary moderating factors. Extensive results showcase that persona agents display strong in-group favoritism, accepting incorrect answers from identity-similar peers at much higher rates than from dissimilar peers. In-group favoritism continues to emerge in defeasible reasoning contexts where no absolute truth exists, and it intensifies as cognitive complexity increases. Furthermore, three intervention strategies--Identity-Blind Instruction, Structured Counterfactual Reasoning, and Heterogeneous Perspective Ensemble--are proposed to mitigate the in-group favoritism.