The deployment of Large Language Models (LLMs) in content generation raises significant safety concerns, particularly regarding the transparency and interpretability of content evaluations. Current methods, primarily focused on binary safety classifications, lack mechanisms for detailed critique, limiting their utility for model improvement and user trust. To address these limitations, we introduce SAFETY-J, a bilingual generative safety evaluator for English and Chinese with critique-based judgment. SAFETY-J utilizes a robust training dataset that includes diverse dialogues and augmented query-response pairs to assess safety across various scenarios comprehensively. We establish an automated meta-evaluation benchmark that objectively assesses the quality of critiques with minimal human intervention, facilitating scalable and continuous improvement. Additionally, SAFETY-J employs an iterative preference learning technique to dynamically refine safety assessments based on meta-evaluations and critiques. Our evaluations demonstrate that SAFETY-J provides more nuanced and accurate safety evaluations, thereby enhancing both critique quality and predictive reliability in complex content scenarios. To facilitate further research and application, we open-source SAFETY-J's training protocols, datasets, and code at https://github.com/GAIR-NLP/Safety-J.
Don't Take the Premise for Granted: Evaluating the Premise Critique Ability of Large Language Models
School of Artificial Intelligence, Jilin University（吉林大学人工智能学院）；Engineering Research Center of Knowledge-Driven Human-Machine Intelligence, MOE, China（知识驱动人机智能工程研究中心，教育部，中国）；International Center of Future Science, Jilin University（未来科学国际中心，吉林大学）
CriticEval: Evaluating Large Language Model as Critic
Shanghai AI Laboratory（上海人工智能实验室）；School of Medical Technology, Beijing Institute of Technology（北京理工大学医学技术学院）；School of Computer Science and Technology, Beijing Institute of Technology（北京理工大学计算机科学与技术学院）
A Structured Framework for Evaluating and Enhancing Interpretive Capabilities of Multimodal LLMs in Culturally Situated Tasks
DJCAD, University of Dundee, United Kingdom（邓迪大学DJCAD部门）；ARG-tech, SSEN, University of Dundee, United Kingdom（邓迪大学）；School of Computer Science, University of Birmingham, United Kingdom（伯明翰大学计算机科学学院）
CASTLE: A Comprehensive Benchmark for Evaluating Student-Tailored Personalized Safety in Large Language Models
East China Normal University（华东师范大学）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Zhejiang University（浙江大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；The Education University of Hong Kong（香港教育大学）
CSSBench: Evaluating the Safety of Lightweight LLMs against Chinese-Specific Adversarial Patterns
Nanyang Technological University（南洋理工大学）；Beijing University of Posts and Telecommunications（北京邮电大学）；Huazhong University of Science and Technology（华中科技大学）
ManagerBench: Evaluating the Safety-Pragmatism Trade-off in Autonomous LLMs
Technion – Israel Institute of Technology（技术学院–以色列理工学院）；Google Research（谷歌研究）；University of Zagreb（Zagreb大学）；Kempner Institute, Harvard University（哈佛大学凯普勒研究所）
RPCBench: A Benchmark for Proactive Premise Critique in LLM-based Recommendation
School of Artificial Intelligence, Jilin University（吉林大学人工智能学院）；Engineering Research Center of Knowledge-Driven Human-Machine Intelligence, MOE, China（教育部知识驱动人机智能工程研究中心）；International Center of Future Science, Jilin University（吉林大学未来科学国际中心）
Faithfulness vs. Safety: Evaluating LLM Behavior Under Counterfactual Medical Evidence
The University of Texas at Austin（德克萨斯大学奥斯汀分校）；Northeastern University（东北大学）；MD Anderson Cancer Center（MD安德森癌症中心）；Georgia Institute of Technology（佐治亚理工学院）
CoSafe: Evaluating Large Language Model Safety in Multi-Turn Dialogue Coreference
The Hong Kong Polytechnic University（香港理工大学）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；Research Centre for Data Science & Artificial Intelligence（数据科学与人工智能研究中心）
Evaluating Large Language Models' Responses to Sexual and Reproductive Health Queries in Nepali
Nepal Applied Mathematics and Informatics Institute for research（尼泊尔应用数学与信息学研究所）；Partnership for Sustainable Development Nepal（尼泊尔可持续发展伙伴关系）；Visible Impact（可见影响）
JMedEthicBench: A Multi-Turn Conversational Benchmark for Evaluating Medical Safety in Japanese Large Language Models
Kyoto University（京都大学）；Hohai University（河海大学）；The University of Tokyo（东京大学）；University of Science and Technology of China（中国科学技术大学）；Hong Kong Polytechnic University（香港理工大学）
MTMCS-Bench: Evaluating Contextual Safety of Multimodal Large Language Models in Multi-Turn Dialogues
University of Notre Dame（诺丁汉大学）；University of California, Los Angeles（加州大学洛杉矶分校）；Georgia Institute of Technology（佐治亚理工学院）；University of Montreal（蒙特利尔大学）
MTCMB: A Multi-Task Benchmark Framework for Evaluating LLMs on Knowledge, Reasoning, and Safety in Traditional Chinese Medicine
School of Software Engineering, Sun Yat-sen University（中山大学软件学院）；Institute of TCM Diagnostics, Hunan University of Chinese Medicine（湖南中医药大学中医诊断研究所）；School of Artificial Intelligence, Guilin University of Electronic Technology（桂林电子科技大学人工智能学院）；Department of Computer Science, Cornell University（康奈尔大学计算机科学系）
Evaluating Psychological Safety of Large Language Models
DAMO Academy, Alibaba Group（阿里巴巴集团达摩院）；School of Computer Science and Engineering, NTU（南洋理工大学计算机科学与工程学院）；School of Social Sciences, NTU（南洋理工大学社会科学学院）；Salesforce Research（Salesforce研究院）；Hupan Lab（湖畔实验室）
TherapyGym: Evaluating and Aligning Clinical Fidelity and Safety in Therapy Chatbots
Department of Computer Science, Stanford University, Stanford, CA, USA（计算机科学系，斯坦福大学，斯坦福，加州，美国）；Department of Psychiatry and Behavioral Sciences, Stanford University, Stanford, CA, USA（精神病学与行为科学系，斯坦福大学，斯坦福，加州，美国）；Department of Biomedical Data Science, Stanford University, Stanford, CA, USA（生物医学数据科学系，斯坦福大学，斯坦福，加州，美国）；University of California, Berkeley, Berkeley, CA, USA（加州大学伯克利分校，伯克利，加州，美国）；The University of Hong Kong, Hong Kong（香港大学，香港）
VULCA-Bench: A Multicultural Vision-Language Benchmark for Evaluating Cultural Understanding
DJCAD, University of Dundee, United Kingdom（邓迪大学DJCAD部门）；University of California, Santa Cruz, USA（加州大学圣克ruz分校）；Analogy AI；East China Normal University, China（华东师范大学）；Nanjing University, China（南京大学）；Department of Mechanical Engineering, School of Engineering, University of Birmingham（伯明翰大学工程学院机械工程系）
We critique recent work on ethics in natural language processing. Those discussions have focused on data collection, experimental design, and interventions in modeling. But we argue that we ought to first understand the frameworks of ethics that are being used to evaluate the fairness and justice of algorithmic systems. Here, we begin that discussion by outlining deontological ethics, and envision a research agenda prioritized by it.
