Light Alignment Improves LLM Safety via Model Self-Reflection with a Single Neuron
Beijing Institute of AI Safety and Governance（北京人工智能安全与治理研究院）；Beijing Key Laboratory of Safe AI and Superalignment（北京安全人工智能与超对齐重点实验室）；Ant Group Co., Ltd.（蚂蚁集团有限公司）；BrainCog Lab., CASIA（CASIA脑认知实验室）；Zhongguancun Academy（中关村学院）
Sicheng Shen, Mingyang Lv, Han Shen, Jialin Wu, Binghao Wang, Zhou Yang, Guobin Shen, Dongcheng Zhao, Feifei Zhao, Yi Zeng
The safety of large language models (LLMs) has increasingly emerged as a fundamental aspect of their development. Existing safety alignment for LLMs is predominantly achieved through post-training methods, which are computationally expensive and often fail to generalize well across different models. A small number of lightweight alignment approaches either rely heavily on prior-computed safety injections or depend excessively on the model's own capabilities, resulting in limited generalization and degraded efficiency and usability during generation. In this work, we propose a safety-aware decoding method that requires only low-cost training of an expert model and employs a single neuron as a gating mechanism. By effectively balancing the model's intrinsic capabilities with external guidance, our approach simultaneously preserves utility and enhances output safety. It demonstrates clear advantages in training overhead and generalization across model scales, offering a new perspective on lightweight alignment for the safe and practical deployment of large language models. Code: https://github.com/Beijing-AISI/NGSD.
Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons
Department of Computer Science and Technology, BNRist（计算机科学与技术系，BNRist）；Shenzhen International Graduate School（深圳国际研究生院）；KIRC, Institute for Artificial Intelligence, Tsinghua University（人工智能研究院，清华大学）
SafeSeek: Universal Attribution of Safety Circuits in Language Models
University of Science；United Arab Emirates University；Nanyang Technological University；Zayed University；Intelligent Science \& Technology Academy of CASIC
Safety Alignment via Constrained Knowledge Unlearning
Harbin Institute of Technology, Shenzhen, China（哈尔滨工业大学（深圳））；University of Macau, China（澳门大学）；Nankai University, China（南开大学）；Zhejiang University, China（浙江大学）；Peng Cheng Laboratory, China（鹏城实验室）；Shaqra University, Saudi Arabia（沙克拉大学）
Multi-Level Safety Continual Projection for Fine-Tuned Large Language Models without Retraining
Beijing Key Laboratory of Safe AI and Superalignment（北京安全人工智能与超对齐重点实验室）；Beijing Institute of AI Safety and Governance（北京人工智能安全与治理研究院）；Brain-inspired Cognitive AI Lab, Institute of Automation, Chinese Academy of Sciences（脑启发认知人工智能实验室，中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Long-term AI（长期人工智能）
Graph-Regularized Sparse Autoencoders for LLM Safety Steering
ELLIS Institute Tübingen（图宾根ELLIS研究所）；Max Planck Institute for Intelligent Systems（智能系统马克斯·普朗克研究所）；Intesa Sanpaolo（Intesa Sanpaolo公司）；University of Southern California（南加州大学）
The Achilles' Heel of LLMs: How Altering a Handful of Neurons Can Cripple Language Abilities
Center for Applied Statistics, School of Statistics, Renmin University of China（中国人民大学统计学院应用统计中心）；Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing（未来区块链与隐私计算北京先进创新中心）；School of Artificial Intelligence, Beihang University（北航人工智能学院）
Diagnosing and Repairing Unsafe Channels in Vision-Language Models via Causal Discovery and Dual-Modal Safety Subspace Projection
Beijing University of Posts and Telecommunications（北京邮电大学）；Huawei Technologies Ltd.（华为技术有限公司）；Peking University（北京大学）；Chongqing University of Posts and Telecommunications（重庆邮电大学）
Behind Harmful Compliance: Behavioral and Mechanistic Divergence Across LLM Jailbreaks
Department of Computer Science（计算机科学系）；Luddy School of Informatics, Computing, and Engineering（信息学、计算与工程学院）；Indiana University Bloomington（印第安纳大学布卢明顿分校）
SafeEvo: Deciphering the Safety Alignment Mechanism and Evolution in Language Models
The University of Hong Kong (HKU)（香港大学）；Chinese Academy of Sciences (CAS)（中国科学院）；Information Engineering University (IEU)（信息工程大学）；Nanyang Technological University (NTU)（南洋理工大学）
EVA: Editing for Versatile Alignment against Jailbreaks
ShanghaiTech University（上海科技大学）；Sun Yat-sen University（中山大学）；State Key Laboratory of Blockchain and Data Security（区块链与数据安全国家重点实验室）；Tsinghua University（清华大学）
SafeSwitch: Steering Unsafe LLM Behavior via Internal Activation Signals
Siebel School of Computing（计算科学系）；Data Science, University of Illinois Urbana-Champaign（数据科学，伊利诺伊大学厄巴纳-香槟分校）；School of Business, Stevens Institute of Technology（商学院，史蒂文斯理工学院）
Jailbreak Instruction-Tuned LLMs via end-of-sentence MLP Re-weighting
Peking University（北京大学）；School of Science（理学院）；Westlake University（西湖大学）；Beijing International Center for Mathematical Research（北京国际数学研究中心）；Center for Machine Learning Research（机器学习研究中心）
ProjLens: Unveiling the Role of Projectors in Multimodal Model Safety
University of Science and Technology of China（中国科学技术大学）；Beijing University of Aeronautics and Astronautics（北京航空航天大学）；Nanyang Technological University（南洋理工大学）；Southwest Jiaotong University（西南交通大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
