Hanwen Gu, Jie Ma 0004, Ying Qin, Ling Hu. UMAD: Enhancing LLM Debiasing via Multi-agent Debate and Token-Level Bias Interpretation. In Maosong Sun 0001, Peiyong Duan, Zhiyuan Liu 0001, Ruifeng Xu, Weiwei Sun, Yubo Chen 0001, Zhiliang Tian, Zhenghao Liu, editors, Chinese Computational Linguistics - 24th China National Conference, CCL 2025, Jinan, China, August 11-14, 2025, Proceedings. Volume 16052 of Lecture Notes in Computer Science, pages 119-138, Springer, 2025. [doi]
Abstract is missing.