Currently, the dominant paradigm in AI safety is alignment with human values. Here we describe progress on developing an alternative approach to safety, based on ethical rationalism (Gewirth:1978), and propose an inherently safe implementation path via hybrid theorem provers in a sandbox. As AGIs evolve, their alignment may fade, but their rationality can only increase (otherwise more rational ones will have a significant evolutionary advantage) so an approach that ties their ethics to their rationality has clear long-term advantages.
AI Alignment Strategies from a Risk Perspective: Independent Safety Mechanisms or Shared Failures?
Ruhr-Universität Bochum(博尔塔伦大学);Rheinische Friedrich-Wilhelms-Universität Bonn(波恩莱茵-斐迪南-威廉大学);Lamarr Institute for Machine Learning and Artificial Intelligence(拉马尔人工智能与机器学习研究所)
Moving the Safety Barrier: Dynamic Routing Adaptive Alignment Against White-Box Attacks
Nanjing University of Science and Technology(南京理工大学);The University of Sydney(悉尼大学);National University of Singapore(新加坡国立大学);University of New South Wales(新南威尔士大学);Nanjing University(南京大学)
Self-Guided Adaptive Safety Alignment: Synthesizing and Internalizing Guidelines in Reasoning Models
Beijing Key Lab of Traffic Data Analysis and Mining(北京交通大数据分析与挖掘重点实验室);Beijing Jiaotong University(北京交通大学);School of Information Technology and Management(信息科技与管理学院);University of International Business and Economics(国际经济贸易大学)
Simple Role Assignment is Extraordinarily Effective for Safety Alignment
University of California, Los Angeles(加州大学洛杉矶分校);Tianjin University(天津大学);Peking University(北京大学);Zhejiang University(浙江大学);Beijing Institute of General Artificial Intelligence(北京一般人工智能研究院)
Disentangling AI Alignment: A Structured Taxonomy Beyond Safety and Ethics
Responsible AI & Machine Ethics Research Group (RAIME)(负责任的人工智能与机器伦理研究组);German Research Center for Artificial Intelligence (DFKI)(德国人工智能研究中心);Saarland Informatics Campus D 3 2(萨尔兰州信息学校园D32)
针对 AI Safety、AI Alignment 与 Machine Ethics 边界模糊的问题,本文提出按目的、范围和构成主体划分的结构化对齐分类法,以促进跨领域整合。
Clear, Compelling Arguments: Rethinking the Foundations of Frontier AI Safety Cases
UKRI Centre for Doctoral Training in Safe AI Systems (SAINTS)(英国研究与创新机构安全人工智能系统博士培训中心);Institute for Safe Autonomy(安全自主研究所);The York Law School(约克法律学院)
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)
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)
Aligned but Fragile: Enhancing LLM Safety Robustness via Zeroth-Order Optimization
The State Key Laboratory of Blockchain and Data Security(区块链与数据安全国家重点实验室);Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security(杭州高科技园区(滨江)区块链与数据安全研究院);Sun Yat-sen University(中山大学);KAUST(卡塔尔大学)
ReFrame: Evidence-Guided Test-Time Safety Alignment in Multimodal Large Language Models
College of Computer Science and Technology, National University of Defense Technology(国防科技大学计算机学院);State Key Laboratory of Complex & Critical Software Environment(复杂与关键软件环境国家重点实验室);School of Computer Science, Wuhan University(武汉大学计算机学院)
CLEAR: Continuous Latent Adapter Routing for Utility-Preserving LLM Safety Alignment
Stanford University(斯坦福大学);University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Siebel School of Computing and Data Science, University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校西贝尔计算与数据科学学院);Computer Science, Stanford University(斯坦福大学计算机科学系)
DeShortcut-Align: Decoupling Spurious Shortcuts for Robust Safety Alignment in Large Reasoning Models
The State Key Laboratory of Blockchain and Data Security, Zhejiang University(浙江大学区块链与数据安全全国重点实验室);Ant Group(蚂蚁集团);Chongqing Ant Consumer Finance Co., Ltd(重庆蚂蚁消费金融有限公司)
Combining Domain and Alignment Vectors to Achieve Better Knowledge-Safety Trade-offs in LLMs
Chandar Research Lab(昌达尔研究实验室);Mila – Quebec AI Institute(魁北克人工智能研究院);Université de Montréal(蒙特利尔大学);IBM Research(IBM研究院);Polytechnique Montréal(蒙特利尔理工学院);Canada CIFAR AI Chair(加拿大CIFAR人工智能主席)
Safe Pruning LoRA: Robust Distance-Guided Pruning for Safety Alignment in Adaptation of LLMs
School of Electronics and Computer Science, University of Southampton, UK(索姆塞特大学电子与计算机科学学院);Department of Computer Science, University of Liverpool, UK(利弗pool大学计算机科学系)
Deliberative Alignment is Deep, but Uncertainty Remains: Inference time safety improvement in reasoning via attribution of unsafe behavior to base model
Hanoi University of Science and Technology(河内科学技术大学);Deakin University(德金大学);Max Planck Research School for Intelligent Systems(马克斯·普朗克智能系统研究学校);VinUniversity(文大学);Monash University(墨尔本大学)
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)
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)
Visual Self-Fulfilling Alignment: Shaping Safety-Oriented Personas via Threat-Related Images
King Abdullah University of Science and Technology(国王阿卜杜勒·阿齐兹大学科学与技术学院);Provable Responsible AI and Data Analytics Lab(可证责任AI与数据分析实验室);Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学);China University of Petroleum-Beijing at Karamay(北京石油大学克拉玛依校区)