Explanation Design in Strategic Learning: Sufficient Explanations That Induce Non-harmful Responses
CISPA Helmholtz Center for Information Security(CISPA海德堡信息安全中心);Mizuho–DL Financial Technology, Co., Ltd.(Mizuho-DL金融科技有限公司);University of Michigan(密歇根大学);Saarland University(萨尔兰州大学)
We study the design of explanations in algorithmic decision-making with strategic agents, individuals who may modify their inputs in response to explanations of a decision maker's (DM's) predictive model. While the demand for algorithmic transparency has led much prior work to assume full model disclosure, in practice DMs typically provide only partial information via explanations, which can cause agents to misinterpret the model and take actions that unintentionally reduce their own utility. A central open question is therefore how DMs should communicate explanations that avoid harming strategic agents while still supporting their own goals, e.g., minimising predictive error. In this work, we analyse widely used explanation methods and establish a necessary condition to prevent explanations from inducing self-harming responses. Furthermore, we show that action recommendation-based explanations (ARexes), which encompass counterfactual explanations, are sufficient to induce all non-harmful responses. Under a conditional homogeneity assumption, this sufficiency extends to ARex-generating methods, echoing the revelation principle in information design. To demonstrate their practical utility, we introduce a simple learning procedure that jointly optimises the predictive model and the explanation-generating policy. Experiments on both synthetic and real-world tasks show that ARexes enable DMs to achieve high predictive performance while preserving agents' utility, offering a principled strategy for safe and effective partial model disclosure.
Strategic Deflection: Defending LLMs from Logit Manipulation
International Artificial Intelligence Center of Morocco(摩洛哥国际人工智能中心);Mohammed VI Polytechnic University(摩洛哥穆莱·伊斯梅尔理工学院);AgriEdge;Sorbonne University, LIP6 - UMR 7606 CNRS(索邦大学,LIP6 - UMR 7606 CNRS)
SAGE: Structured Strategic Reasoning for Efficient LLM Game Playing
The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Johns Hopkins University(约翰斯·霍普金斯大学);Microsoft(微软);Fudan University(复旦大学);University of Science and Technology of China(中国科学技术大学)
Communication Enhances LLMs' Stability in Strategic Thinking
Network Science Institute Northeastern University(东北大学网络科学研究所);Department of Mechanical and Industrial Engineering, Institute of Experiential AI(机械与工业工程系,体验式人工智能研究所)
Mitigating Many-shot Jailbreak Attacks with One Single Demonstration
Zhejiang University(浙江大学);Nanyang Technological University(南洋理工大学);Sun Yat-sen University(中山大学);University of Science and Technology of China(中国科学技术大学);Virginia Tech(弗吉尼亚理工大学)
AM-Bench: A Unified Taxonomy and Evaluation Suite for Agentic Misalignment
University of Toronto(多伦多大学);Vector Institute(矢量研究院);EuroSafeAI;Carnegie Mellon University(卡内基梅隆大学);Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所)
AgentHazard: A Benchmark for Evaluating Harmful Behavior in Computer-Use Agents
Alibaba Group(阿里巴巴集团);Fudan University(复旦大学);Hunan Institute of Advanced Technology(湖南先进技术研究院);Deakin University(迪肯大学);Singapore Management University(新加坡管理大学)
Beyond Independent Manipulation: Individual Fairness-aware Strategic Classification with Peer Imitation
College of Computer Science and Technology, National University of Defense Technology(国防科技大学计算机科学与技术学院);School of Mathematical Sciences, Peking University(北京大学数学学院);Institute for Theoretical Computer Science, Shanghai University of Finance and Economics(上海财经大学理论计算机科学研究所);Information Technology Development, Aetos Capital Group, Sydney(悉尼Aetos资本集团信息技术部);Faculty of Computing, Harbin Institute of Technology(哈尔滨工业大学计算机学院);Department of Computer Science and Technology, Tsinghua University(清华大学计算机科学与技术系)
Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise and Reconstruction
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络空间安全学院);RealAI;Tsinghua University(清华大学)
Reasoning Like an Economist: Post-Training on Economic Problems Induces Strategic Generalization in LLMs
Duke University(杜克大学);EPIC Lab, Shanghai Jiao Tong University(上海交通大学EPIC实验室);Qwen Team, Alibaba Group(阿里集团Qwen团队);University of Pennsylvania(宾夕法尼亚大学);The University of Chicago(芝加哥大学)
Allocating Indivisible Goods to Strategic Agents: Pure Nash Equilibria and Fairness
School of Mathematics, Statistics and Actuarial Science, University of Essex(埃塞克斯大学数学、统计与精算科学学院);Archimedes/Athena RC(阿基米德/雅典娜研究中心);Department of Computer Science, University of Liverpool(利物浦大学计算机科学系);Department of Computer, Control, and Management Engineering, Sapienza University of Rome(罗马大学计算机、控制与管理工程系);Input Output Global (IOG)(输入输出全球公司);Institute for Logic, Language and Computation, University of Amsterdam(阿姆斯特丹大学逻辑、语言与计算研究所)
X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents
University of California, Los Angeles(加州大学洛杉矶分校);University of Washington(华盛顿大学);Qatar Computing Research Institute(卡塔尔计算研究所);Google(谷歌);Stanford University(斯坦福大学)