Multi-Persona Thinking for Bias Mitigation in Large Language Models

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chen, Yuxing, Luo, Guoqing, Wu, Zijun, Mou, Lili
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910151593689088
author Chen, Yuxing
Luo, Guoqing
Wu, Zijun
Mou, Lili
author_facet Chen, Yuxing
Luo, Guoqing
Wu, Zijun
Mou, Lili
contents Large Language Models (LLMs) exhibit social biases, which can lead to harmful stereotypes and unfair outcomes. We propose \textbf{Multi-Persona Thinking (MPT)}, a simple inference-time framework that reduces social bias by encouraging reasoning from multiple perspectives. MPT guides the model to consider contrasting social identities, such as male and female, together with a neutral viewpoint. These viewpoints then interact through an iterative reasoning process to identify and correct biased judgments. This design transforms the potential weakness of persona assignment into a mechanism to mitigate bias. We evaluate MPT on two widely used bias benchmarks with both open-source and closed-source models. Our results show that MPT achieves a lower bias than the existing prompting-based methods while maintaining the core reasoning ability.
format Preprint
id arxiv_https___arxiv_org_abs_2601_15488
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Multi-Persona Thinking for Bias Mitigation in Large Language Models
Chen, Yuxing
Luo, Guoqing
Wu, Zijun
Mou, Lili
Computation and Language
Artificial Intelligence
Large Language Models (LLMs) exhibit social biases, which can lead to harmful stereotypes and unfair outcomes. We propose \textbf{Multi-Persona Thinking (MPT)}, a simple inference-time framework that reduces social bias by encouraging reasoning from multiple perspectives. MPT guides the model to consider contrasting social identities, such as male and female, together with a neutral viewpoint. These viewpoints then interact through an iterative reasoning process to identify and correct biased judgments. This design transforms the potential weakness of persona assignment into a mechanism to mitigate bias. We evaluate MPT on two widely used bias benchmarks with both open-source and closed-source models. Our results show that MPT achieves a lower bias than the existing prompting-based methods while maintaining the core reasoning ability.
title Multi-Persona Thinking for Bias Mitigation in Large Language Models
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2601.15488