LLM Safety Alignment

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

25 papers in the last four weeks, up 14% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 236

All topics

ReSI: Recursive Safety Improvement toward Resistant and Resilient AI
Oct 8, 2026Jingnan Zheng, Dongcheng Zhang, Yi Zhang +10LLM Safety Alignment Recursive Self-Improvement
Shanghai AI Laboratory · National University of Singapore · Shanghai Jiao Tong University +2
Distillation for Incrimination and Distillation for Capabilities
Oct 7, 2026Sebastian Prasanna, Jacqueline Tay, Alek WestoverLLM Safety Alignment Language Model Distillation
Redwood Research
How Narrative Wrapping Affects LLM Refusal: A Cross-Language Benchmark and Defense
Oct 7, 2026Zhankai Ye, Yanning Wang, Yukai Jin +5Refusal Behavior in Language Models LLM Safety Alignment
Florida State University · Texas Christian University · University of Pennsylvania +1
SLDR: Defending Against Malicious Fine-tuning via Selective Layers Recovery and Dynamic Routing
Oct 7, 2026Hui Zhang, Yachao Yuan, Jiayun Wang +3LLM Security LLM Safety
North China Electric Power University · Southeast University · Soochow University +1
SafeEvo: Deciphering the Safety Alignment Mechanism and Evolution in Language Models
Oct 7, 2026Miao Yu, Hao Huang, Lu Yuan +3LLM Safety Alignment LLM Alignment
The University of Hong Kong (HKU) · Chinese Academy of Sciences (CAS) · Information Engineering University (IEU) +1
The Model Plants the Trigger: Answer-Side Backdoor Attacks in Multi-Turn Large Language Models
Oct 6, 2026Yibo Zhang, Tianrong Guan, Liang Lin +3LLM Backdoor Attacks Backdoor Attacks
Queen Mary University of London, UK · Squirrel AI Learning, USA
Safe Context Switching for Agents in the Wild: Mitigating Subspace Interference via Orthogonal Adaptation
Oct 4, 2026Akash Das, Ishan RoyLLM Safety Alignment LLM Safety
Fidelity Investments
TRACE: Trajectory Return Attribution and Contrastive Erasure for Multi-Turn Safety
Oct 1, 2026Fengpeng Li, Kemou Li, Qizhou Wang +3LLM Fine-Tuning Adversarial Attacks on LLMs
PRADA Lab, King Abdullah University of Science and Technology · State Key Laboratory of Internet of Things for Smart City, University of Macau · Imperfect Information Learning Team, RIKEN Center for Advanced Intelligence Project +1
CodeMimicry: Exploiting Safety Generalization Lag in Large Language Models via Structured Code Completion
Sep 30, 2026Zhen Liang, Hai Huang, Wentao ChenAdversarial Attacks on LLMs Jailbreak Attacks
School of Computer Science and Technology, Zhejiang Sci-Tech University · Zhejiang Key Laboratory of Digital Fashion and Data Governance, Zhejiang Sci-Tech University · China Academy of Information and Communications Technology
Faithful Dual-constrained Erasure for Robust LLM Safety Alignment
Sep 30, 2026Jiaqing Li, Shide Zhou, Zhibo Zhang +3LLM Safety Alignment Machine Unlearning
Huazhong University of Science and Technology · Hubei University
Alignment via Training Against Probes Without Losing Monitorability
Sep 29, 2026Lena Libon, Alexander Panfilov, Ben Rank +3Fine-Tuning LLM Safety Alignment
ETH Zurich · ELLIS Institute Tübingen, MPI for Intelligent Systems, Tübingen AI Center
ACTR: Aligning Thoughts and Responses for Multilingual Safety in Reasoning LLMs
Sep 29, 2026Xianhui Zhang, Jian Yu, Chengyu Xie +6Adversarial Attacks on LLMs LLM Safety Alignment
Nanjing University of Science and Technology, Nanjing, China · National University of Singapore, Singapore · Beihang University, Beijing, China
Safer Content or Firmer Refusals? A Hybrid Perturbation Defense for Alignment under Harmful Fine-tuning
Sep 29, 2026Muhammad Zeeshan Akram, Mufid Kamel Marican, Anvesh Reddy Yenugu +2LLM Safety Alignment Adversarial Robustness of Language Models
University of Louisville Louisville, Kentucky, USA
Constitutional adapters: Inference-time interventions for misalignment and misuse
Sep 29, 2026Adam S. Lowet, Mark KurzejaLLM Safety Alignment LLM Jailbreak Attacks
Anthropic Fellows Program · Independent
The Safety Operator: Modulating the Expression of Safety Instructions via Spectral Optimization
Sep 29, 2026Benoit Dherin, Michael Munn, Xavier Gonzalvo +14LLM Safety Alignment LLM Safety
Google Research · Cambridge University · Google DeepMind +2
Towards Mitigating Deceptive Safety Alignment in Large Reasoning Models
Sep 28, 2026Xiangyu Zhou, Saleh Zare Zade, Rafi Ibn Sultan +2Language Model Safety Evaluation Deception in Language Models
Wayne State University
See it, Say it, Sorted: Mechanistic Diagnosis and Parameter-Space Mitigation of Emergent Misalignment in LLMs
Sep 28, 2026Weiqiao Que, Ruizhe Li, Chengyu Wang +3Emergent Misalignment in Language Models LLM Safety Alignment
School of Computer Science and Technology, East China Normal University, China · School of Computer Science, University of Birmingham, UK · Alibaba Group, China +2
DeShortcut-Align: Decoupling Spurious Shortcuts for Robust Safety Alignment in Large Reasoning Models
Sep 28, 2026Qirui Liu, Yichen Sun, Yan Wang +4LLM Safety Alignment Adversarial Robustness of Language Models
The State Key Laboratory of Blockchain and Data Security, Zhejiang University · Ant Group · Chongqing Ant Consumer Finance Co., Ltd
When Do Model Internals Help? Exploring the Role of Representation Engineering in LLM Safety
Sep 28, 2026Tianyi Guan, Jianhui Chen, Liangming PanLanguage Model Safety Evaluation LLM Interpretability
State Key Laboratory of Multimedia Information Processing, Peking University · School of Computer Science, Peking University
EOPSA: Efficient On-Policy Self-Distilled Safety Alignment
Sep 28, 2026Qirui Liu, Yichen Sun, Yan Wang +5On-Policy Self-Distillation Selective Knowledge Distillation
The State Key Laboratory of Blockchain and Data Security, Zhejiang University · Ant Group
SafeMol: Dual-Modality Safety Alignment for Molecular Multimodal Models
Sep 27, 2026Xinmiao Wang, Ruijie Wang, Menghui Wang +5Adversarial Attacks on LLMs LLM Safety Alignment
Beihang University · China CITIC Bank · Stable AI +1
Syndrome, Synergy, and Safety: Structured Reasoning and Knowledge-Driven Alignment for TCM Prescription Generation
Sep 22, 2026Zheng Chen, ZhiCheng Du, Haoxuan Li +1LLM Alignment CoT Reasoning
Tsinghua University · Guangdong Provincial Laboratory of Traditional Chinese Medicine Hengqin
A $^2$ Safe: Counterfactual Evidence-Aligned Adaptive Agent Collaboration for Safe and Effective Visual Question Answering
Sep 21, 2026Quanxing Xu, Ling Zhou, Xian Zhong +4Visual Question Answering LLM Safety Alignment
School of Computer Science and Engineering, Macau University of Science and Technology, Macao SAR 999078, China · Hubei Key Laboratory of Transportation Internet of Things, School of Artificial Intelligence, Wuhan University of Technology, Wuhan 430070, China · Oulu School, Nanjing Institute of Technology, Nanjing 210096, China +1
AUDITPLAN: Commit, Then Answer for Auditable Safety Alignment
Sep 16, 2026Sai Sri Pushpa Jampani, Kshitij Mishra, Asif EkbalLLM Alignment LLM Auditing
Indian Institute of Technology Patna, Bihar, India
Beyond Routine Compliance: Cunning Data Cultivates Safety Vigilance in Large Language Models
Sep 16, 2026Youjia Wang, Lin Xu, Yang Sun +3LLM Safety Alignment LLM Safety
Huawei Technology Inc
First Token Matters: Understanding Safety Collapse in Large Reasoning Models
Sep 16, 2026Yizheng Yang, Haining Yu, Yuechen Wang +4LLM Safety Alignment Inference-Time Intervention
Harbin Institute of Technology, Harbin, China · Guangzhou University, Guangzhou, China · City University of Macau, Macau, China
AI Safety: Not Optional, Not Later
Sep 14, 2026Qinghua Lu, Yoshua BengioAI Assurance AI Accountability
CSIRO, Australia · LawZero, Canada · Université de Montréal, Canada +1
An Efficient and Modular Framework for Targeted Harm Mitigation in LLMS
Sep 12, 2026Roberto Campbell, Momin Abbass, Muneeza Azmat +5LLM Safety Alignment Low-Rank Adaptation
University of California, Santa Cruz · IBM Research
Suan: Rectifying Direct Preference Safety Alignment in Large Language Models
Sep 8, 2026Oleksandr Cherednichenko, Roman KlypaLLM Alignment LLM Safety Alignment
Department of Mathematics and Mathematical Statistics Integrated Science Lab, Umeå University Umeå, Sweden · Univ. Grenoble Alpes, CNRS, Grenoble INP, LJK 38000 Grenoble, France
Does Deeper Reasoning Compromise Alignment? Revealing and Mitigating of Alignment Collapse in Large Reasoning Models
Sep 8, 2026Yu-Hang Wu, Yu-Jie Xiong, Henghua Zhang +3Adversarial Attacks on LLMs Jailbreak Attacks
Shanghai University of Engineering Science · The Hong Kong University of Science and Technology · A * STAR

Oct 8, 2026, cs.CRJ/K move · Enter open · S save

ReSI: Recursive Safety Improvement toward Resistant and Resilient AI

Jingnan Zheng, Dongcheng Zhang, Yi Zhang, Ming Zhang+9

Shanghai AI Laboratory · National University of Singapore · Shanghai Jiao Tong University+2

LLM Safety Alignment Recursive Self-Improvement Language Model Safety Evaluation

Open paper AskPDF arXiv

Recursive self-improvement, the participation of AI systems in improving their own capabilities, is beginning to move from theoretical prospect to practice, posing both challenges and opportunities for safety alignment. Models evolve through frequent updates, and their safety alignment requires continual adaptation to each new checkpoint. Meanwhile, with evolving red-teaming methods exposing new vulnerabilities, safety improvement for each checkpoint needs to mitigate exposed vulnerabilities and generalize to risks not yet revealed. Following R

^2

AI, we term these goals resistance to known threats and resilience to unforeseen risks. Recursive self-improvement, in turn, inspires an approach to both goals: safety alignment could likewise advance through successive rounds of evaluation and update. We therefore introduce ReSI, a recursive safety improvement framework that implements this approach through automated research. In each round, ReSI applies diverse red-teaming methods to identify vulnerabilities in the current target model, develops training recipes, and promotes the update with the largest safety gain among those passing a Pareto gate on capability retention as the next target model. Across four dense and mixture-of-experts models, ReSI matches or exceeds evaluated frontier models on in-distribution and out-of-distribution safety benchmarks, and outperforms alignment baselines on nearly all safety evaluations while largely preserving general capabilities. In particular, ReSI reduces the mean X-Teaming attack success rate across the four models from 86.01% to 31.45%, well below GPT-5.6-Luna's leading frontier result of 56.69%, indicating stronger resilience to attacks unseen during training. These findings support recursive safety improvement as a practical path toward resistant and resilient AI.

Momentum

Related topics

Latest papers 236