一作ACL 2026Findings· Findings of ACL
Multi-Persona Thinking for Bias Mitigation in Large Language Models
Yuxing Chen · Guoqing Luo · Zijun Wu · Lili Mou
摘要
Large Language Models (LLMs) exhibit social biases, which can lead to harmful stereotypes and unfair outcomes. We propose 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...