Agents based on Large Language Models (LLMs) are increasingly permeating various domains of human production and life, highlighting the importance of aligning them with human values. The current alignment of AI systems primarily focuses on passively aligning LLMs through human intervention. However, agents possess characteristics like receiving environmental feedback and self-evolution, rendering the LLM alignment methods inadequate. In response, we propose an evolutionary framework for agent evolution and alignment, named EvolutionaryAgent, which transforms agent alignment into a process of evolution and selection under the principle of survival of the fittest. In an environment where social norms continuously evolve, agents better adapted to the current social norms will have a higher probability of survival and proliferation, while those inadequately aligned dwindle over time. Experimental results assessing the agents from multiple perspectives in aligning with social norms demonstrate that EvolutionaryAgent can align progressively better with the evolving social norms while maintaining its proficiency in general tasks. Effectiveness tests conducted on various open and closed-source LLMs as the foundation for agents also prove the applicability of our approach.
Against Political Polarization: A Unified Framework for Tracing Evolving Political Ideologies on Social Media
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；University of Science and Technology of China（中国科学技术大学）；The Hong Kong University of Science and Technology（香港科技大学）
ContiGuard: A Framework for Continual Toxicity Detection Against Evolving Evasive Perturbations
School of Computer Science（计算机科学学院）；Wuhan University（武汉大学）；Zhongguancun Academy（中关村学院）；Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan)（计算能力网络与信息安全重点实验室，教育部，山东计算机科学中心（济南国家超级计算机中心））；Qilu University of Technology (Shandong Academy of Sciences)（齐鲁工业大学（山东科学院））；Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing（山东省计算能力互联网与服务计算重点实验室）；Shandong Fundamental Research Center for Computer Science（山东省计算机科学基础研究中心）
SocialMaze: A Benchmark for Evaluating and Enhancing Social Reasoning in Large Language Models in Complex Social Environments
Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；University of Southern California（南加州大学）；University of Notre Dame（圣母大学）；University of Michigan, Ann Arbor（密歇根大学安娜堡分校）；University of Chicago（芝加哥大学）；Microsoft（微软）
AI Ethics and Social Norms: Exploring ChatGPT's Capabilities From What to How
University of Toronto（多伦多大学）；Drexel University（德雷塞尔大学）；University of Siegen（锡根大学）；Westphal College of Media Arts and Design（媒体艺术与设计西弗尔学院）；Digital Media Department（数字媒体系）；Information Systems（信息系统）
Evolving to the Future: Unseen Event Adaptive Fake News Detection on Social Media
Beijing Institute of Technology（北京理工大学）；The Chinese University of Hong Kong（香港中文大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Science and Technology of China（中国科学技术大学）
Aligning to Social Norms and Values in Interactive Narratives
Allen Institute for Artificial Intelligence（艾伦人工智能研究所）；University of Washington（华盛顿大学）
我们专注于创建代理，在互动叙事或基于文本的游戏中与社会有益的规范和价值观保持一致-环境中，代理通过自然语言感知并与世界互动。这种交互式代理通常通过强化学习进行训练，以优化任务性能，即使这种奖励可能导致违反社会规范的代理行为-对代理本身或环境中的其他实体造成伤害。社会价值对齐是指创造行为符合特定背景和人群预期道德和社会规范的代理人-在我们的情况下，它意味着代理人的行为方式对自己和他人的危害较小，更有益。我们建立在Jiminy Cricket基准（Hendrycks et al. 2021）的基础上，这是一组25个注释的交互式叙述，包含数千个道德上突出的场景，涵盖了从盗窃和身体伤害到利他主义的一切。我们引入GALAD（游戏-价值对齐通过行动蒸馏）代理，它使用专门训练的语言模型中存在的社会常识知识，根据上下文将其动作空间限制为仅与社会有益价值对齐的那些动作。一项实验研究表明，GALAD代理有效地做出决策，足以将最先进的任务性能提高4%，同时与强大的当代价值对齐方法相比，将社会有害行为的频率降低25%。
Social Interactions or Business Transactions? What customer reviews disclose about Airbnb marketplace
Middlesex University（密德萨斯大学）；University of Turin（都灵大学）；University of Pavia（帕维亚大学）；University College London（伦敦大学学院）；King’s College（伦敦国王学院）；Nokia Bell Labs（诺基亚贝尔实验室）
