Comments15 pages. Accepted at the CTB, FAGEN, and AI4GOOD workshops at ICML 2026 in Seoul, South Korea. Code and dataset: this https URL (https://github.com/ArtKanke/DeflectBench)
机构
*
Human Nature Lab, Yale University, New Haven, USA(耶鲁大学人类本质实验室)
;
Yale Institute for Network Science, Yale University, New Haven, USA(耶鲁大学网络科学研究所)
;
Université Paris Saclay, Université Paris Cité, ENS Paris Saclay, CNRS, SSA, INSERM, Centre Borelli, Gif-sur-Yvette, France(巴黎萨克雷大学、巴黎城市大学、巴黎萨克雷高等师范学院、国家科学研究中心、SSA、国家医学研究院、Borelli研究中心,法国)
;
Department of Informatics and Telecommunications, University of Peloponnese, Peloponnese, Greece(希腊皮洛斯大学信息与电信系)
机构
*
Zhongguancun Academy(中关村学院)
;
Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所)
;
School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院)
;
University of Manchester(曼彻斯特大学)
;
Tongji University(同济大学)