Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training
School of Data Science, The Chinese University of Hong Kong, Shenzhen, China（数据科学学院，香港中文大学（深圳））；Tencent AI Lab（腾讯人工智能实验室）；The Chinese University of Hong Kong（香港中文大学）；Shenzhen Research Institute of Big Data, China（深圳大数据研究院）
This study addresses a critical gap in safety tuning practices for Large Language Models (LLMs) by identifying and tackling a refusal position bias within safety tuning data, which compromises the models' ability to appropriately refuse generating unsafe content. We introduce a novel approach, Decoupled Refusal Training (DeRTa), designed to empower LLMs to refuse compliance to harmful prompts at any response position, significantly enhancing their safety capabilities. DeRTa incorporates two novel components: (1) Maximum Likelihood Estimation (MLE) with Harmful Response Prefix, which trains models to recognize and avoid unsafe content by appending a segment of harmful response to the beginning of a safe response, and (2) Reinforced Transition Optimization (RTO), which equips models with the ability to transition from potential harm to safety refusal consistently throughout the harmful response sequence. Our empirical evaluation, conducted using LLaMA3 and Mistral model families across six attack scenarios, demonstrates that our method not only improves model safety without compromising performance but also surpasses baseline methods in defending against attacks.
Can LLMs Refuse Questions They Do Not Know? Measuring Knowledge-Aware Refusal in Factual Tasks
Department of Computer Science, City University of Hong Kong（香港城市大学计算机科学系）；Harbin Institute of Technology（哈尔滨工业大学）；College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算机与数据科学学院）；School of Computer Science and Engineering, Central South University（中南大学计算机科学与工程学院）
Please refuse to answer me! Mitigating Over-Refusal in Large Language Models via Adaptive Contrastive Decoding
School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen University（中山大学信息科学与技术学院深圳校区）；School of Information, Central University of Finance and Economics（中央财经大学信息学院）；School of Artificial Intelligence, Beijing Normal University（北京师范大学人工智能学院）；School of Computing Technologies, RMIT University（皇家墨尔本理工大学计算技术学院）
Deactivating Refusal Triggers: Understanding and Mitigating Overrefusal in Safety Alignment
University of California, Santa Barbara（加州大学圣巴巴拉分校）；Johns Hopkins University（约翰霍普金斯大学）；Michigan State University（密歇根州立大学）；University of Mississippi（密苏里州立大学）
Utilize the Flow before Stepping into the Same River Twice: Certainty Represented Knowledge Flow for Refusal-Aware Instruction Tuning
Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Peking University（北京大学）；Southwest Jiaotong University（西南交通大学）；Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences（中国科学院大学杭州高等研究院）
GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation
Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Peking University（北京大学）；Southwest Jiaotong University（西南交通大学）；Shanghai Jiaotong University（上海交通大学）；Chinese University of Hong Kong（香港中文大学）
Decomposing Refusal Steering in Mixture-of-Experts Models
Department of Interdisciplinary Studies（交叉学科研究部）；University of Montana（蒙大拿大学）；Department of Pharmacy Practice & Science（药学与科学系）；University of Arizona（亚利桑那大学）；European Bioinformatics Institute（欧洲生物信息研究所）；European Molecular Biology Laboratory（欧洲分子生物学实验室）；Wellcome Genome Campus（沃氏基因组校园）
EVOREFUSE: Evolutionary Prompt Optimization for Evaluation and Mitigation of LLM Over-Refusal to Pseudo-Malicious Instructions
Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University（航天信息安全部门、教育部、武汉大学计算机科学与工程学院）；Ant Group（蚂蚁集团）；Ant International（蚂蚁国际）；School of Computing Technologies, Royal Melbourne Institute of Technology（皇家墨尔本理工学院计算机技术学院）
