Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2605.01329 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910185186918400 |
|---|---|
| author | Lei, Shijun Wang, Hongyu Liang, Yunji Zheng, Haowen Guo, Bin Yu, Zhiwen |
| author_facet | Lei, Shijun Wang, Hongyu Liang, Yunji Zheng, Haowen Guo, Bin Yu, Zhiwen |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_01329 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Truth or Tribe: How In-group Favoritism Prioritize Facts in Persona Agents Lei, Shijun Wang, Hongyu Liang, Yunji Zheng, Haowen Guo, Bin Yu, Zhiwen Artificial Intelligence Computers and Society 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. |
| title | Truth or Tribe: How In-group Favoritism Prioritize Facts in Persona Agents |
| topic | Artificial Intelligence Computers and Society |
| url | https://arxiv.org/abs/2605.01329 |