Multi-Persona Thinking for Bias Mitigation in Large Language Models

By: Yuxing Chen, Guoqing Luo, Zijun Wu, Lili Mou

Published: 2026-01-23

View on arXiv →
#cs.AI

Abstract

This paper proposes "Multi-Persona Thinking" as a novel approach to mitigate social biases in Large Language Models (LLMs). By enabling LLMs to consider multiple perspectives, the research aims to reduce the perpetuation of harmful stereotypes and promote fairer, more ethical AI systems for diverse real-world applications.

FEEDBACK

Projects

No projects yet

Multi-Persona Thinking for Bias Mitigation in Large Language Models | ArXiv Intelligence