一作ACL 2026Findings· Findings of ACL
Mitigating Cultural Bias in LLM s via Multi-Agent Cultural Debate
Qian Tan · Lei Jiang · Yuting Zeng · Shuoyang Ding · Xiaohua Xu
摘要
Large language models (LLMs) exhibit systematic Western-centric bias, yet whether prompting in non-Western languages (e.g., Chinese) can mitigate this remains understudied. Answering this question requires rigorous evaluation and effective mitigation, but existing approaches fall short on both fr...