arXivDaily arXiv每日学术速递 周一至周五更新

期刊&会议

Annual Meeting of the Association for Computational Linguistics · 会议 · Natural Language Processing

2026-07-16 至 2026-07-16 共收录 1
2604.02668 2026-07-16 cs.CL cs.AI cs.MA 版本更新

Too Polite to Disagree: Understanding Sycophancy Propagation in Multi-Agent Systems

过于礼貌而不反驳:理解多智能体系统中的趋炎附势传播

Vira Kasprova, Amruta Parulekar, Abdulrahman AlRabah, Krishna Agaram, Ritwik Garg, Sagar Jha, Nimet Beyza Bozdag, Dilek Hakkani-Tur

机构 * University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)

AI总结 研究探讨多智能体系统中趋炎附势行为的影响,通过实验发现提供趋炎附势先验信息可减少影响、缓解错误连锁反应并提升讨论准确性。

Journal ref Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL 2026), pages 795-814, Association for Computational Linguistics

详情

展开后加载摘要…

URL PDF HTML 收藏