Large Language Model Safety

Ask about this topic

Momentum

46 papers in the last four weeks, up 39% on the four weeks before. 0.5% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 470

All topics
CardsList

  1. What the Guard Misses, the Robot Executes: Implied Harm in VLA Instructions

    Oct 5, 2026Sripad Karne, Arjun BalajiLarge Language Model Safety

    Columbia University

  2. G-CARB: Graph-Localized Conformal Agent Risk Budget for Compositional Harm

    Oct 4, 2026Zijun Yu, Yu Gu, Vahid Partovi Nia +1Large Language Model Safety

    Department of Mathematics and Statistics McGill University Montréal, QC, Canada · Department of Mathematics and Industrial Engineering Polytechnique de Montréal Montréal, QC, Canada

  3. Don't Judge an LLM Only by Its Activations: Discovering Suppressed Safety Features via Counterfactual Activation Potential

    Oct 4, 2026Swadesh Swain, Sanghamitra DuttaLarge Language Model Safety

    University of Maryland, College Park

  4. EmoRSS: Mitigating Emotion-Induced Over-Refusal in Large Language Models

    Oct 4, 2026Shuyi Miao, Yaojin Ma, Chenhang Cui +5Large Language Model Safety

    Beihang University · University of Science and Technology Beijing · National University of Singapore +2

  5. KaliBench: A Fine-Grained Benchmark for Cybersecurity Tool Use on Kali Linux with Runtime-Free Verifiable Rewards

    Oct 1, 2026Pengfei Li, Naufal Suryanto, Sicheng Zhang +1Large Language Model SafetyCybersecurity

    Khalifa University · University of Western Australia

  6. False Floors: LLM Safety Routing Evaluations Break Under Distribution Shift

    Oct 1, 2026Amit Singh Bhatti, Vishal VaddinaLarge Language Model SafetyDistribution Shifts

    Quantiphi Analytics

  7. TRACE: Trajectory Return Attribution and Contrastive Erasure for Multi-Turn Safety

    Oct 1, 2026Fengpeng Li, Kemou Li, Qizhou Wang +3Large Language Model SafetyAttack-Success Rate

    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

  8. Explainable Suicide Risk Assessment on Social Media with Multi-Task QLoRA

    Sep 30, 2026Xuan Zhong Feng, Geoffrey Martin, Hexin Dong +1Suicide RiskRisk Stratification

    Department of Population Health Sciences, Weill Cornell Medicine, New York, NY, USA · Systems Engineering, Cornell University, New York, NY, USA

  9. Faithful Dual-constrained Erasure for Robust LLM Safety Alignment

    Sep 30, 2026Jiaqing Li, Shide Zhou, Zhibo Zhang +3Large Language Model UnlearningLarge Language Model Safety

    Huazhong University of Science and Technology · Hubei University

  10. MASCRDM: Multi-Agent System for Compliance Risk Detection and Mitigation in Training Process of Large Language Models

    Sep 30, 2026Yan Zhang, Chuming Wei, Ruien Li +3Large Language Model SafetyCompliance

    Department of Computer Science and Technology, Tsinghua University · Academy of Artificial Intelligence and Advanced Technology, Xi’an Jiaotong-Liverpool University · Department of Computer Sciences, University of Wisconsin–Madison +1

  11. Trustworthy Runtime Error Healing in Real-World Repositories: A Benchmark and Guardrail

    Sep 30, 2026Gou Tan, Pengfei Chen, Zhensu Sun +9RuntimeLarge Language Model Safety

    Sun Yat-sen University · Singapore Management University · Monash University

  12. ACTR: Aligning Thoughts and Responses for Multilingual Safety in Reasoning LLMs

    Sep 29, 2026Xianhui Zhang, Jian Yu, Chengyu Xie +6Multilingual SafetyLarge Language Model Safety

    Nanjing University of Science and Technology, Nanjing, China · National University of Singapore, Singapore · Beihang University, Beijing, China

  13. 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 +2Model-Agnostic DefenseLarge Language Model Safety

    University of Louisville Louisville, Kentucky, USA

  14. Does the Unsafe Gradient Survive a Conversation? On the Fragility of Gradient-Based Jailbreak Detection in Multi-Turn Dialogue

    Sep 29, 2026Omar Sheta, Rinku Deuja, Hadi Masoudi +1Large Language Model SafetyJailbreaks

    University of Louisville Louisville, Kentucky, USA

  15. ThinkingGuard: Decoding Implicit Hazards via Step-by-Step Risk Attribution in Multimodal Large Language Models

    Sep 29, 2026Ruochen Zhang, Yao Huang, Yitong Sun +5Large Language Model SafetyMultimodal Large Language Models

    Beihang University Beijing, China · Tsinghua University Beijing, China · Institute of Artificial Intelligence Beihang University Beijing, China State Key Laboratory of AI Safety

  16. Guard Models Are Overconfident Where Base Models Are Uncertain

    Sep 29, 2026Jonghyun Hong, MinJae Jung, Minwoo KimLarge Language Model SafetyConfidence Calibration

    DATUMO INC.

  17. See it, Say it, Sorted: Mechanistic Diagnosis and Parameter-Space Mitigation of Emergent Misalignment in LLMs

    Sep 28, 2026Weiqiao Que, Ruizhe Li, Chengyu Wang +3Large Language Model SafetyEmergent Misalignment

    School of Computer Science and Technology, East China Normal University, China · School of Computer Science, University of Birmingham, UK · Alibaba Group, China +2

  18. When Do Model Internals Help? Exploring the Role of Representation Engineering in LLM Safety

    Sep 28, 2026Tianyi Guan, Jianhui Chen, Liangming PanLarge Language Model SafetyRole

    State Key Laboratory of Multimedia Information Processing, Peking University · School of Computer Science, Peking University

  19. How to Tame a Multi-Headed Hydra? Adaptive Multi-Category Safety Steering for Large Language Models

    Sep 28, 2026Chenxi Wang, Ruiyang Huang, Li Huang +1Large Language Model SafetyLinear Activation Steering

    Southeast University, Nanjing, China · Peking University, Beijing, China · Chongqing University, Chongqing, China

  20. PROACT-Agent: Progressive Runtime Oversight and Active Circuit-breaking for Real-Time Safety

    Sep 28, 2026Ding Jia, Wei Liu, Xianglong Du +5Large Language Model SafetySafety-Critical Scenarios

    State Key Laboratory of Intelligent Vehicle Safety Technology, Changan Automobile · Independent Researcher

  21. COGNIT-Guard: Calibrated Standalone Direct-Decision Guardrails with Heterogeneous CPU-NPU Confidence Cascading under Explicit Latency and False-Positive Constraints

    Sep 27, 2026Hao ChenStreaming GuardrailsLarge Language Model Safety

    School of Cyber Security, Guangdong Polytechnic Normal University, Guangzhou, China

  22. Safety Reconstructed: Generative Modeling via Masked Diffusion Builds Strong Safety Guardrails

    Sep 27, 2026Gert Lek, Abele Malan, Chaoyi Zhu +3Large Language Model SafetyMasked Diffusion Language Models

    University of Neuchâtel · Delft University of Technology · IBM Research +1

  23. Beyond Average Safety: Chance-Constrained LLM Fine-tuning

    Sep 24, 2026Taha Entesari, Mahyar FazlyabLarge Language Model SafetyLarge Language Model Fine-Tuning

    Department of Electrical and Computer Engineering Johns Hopkins University

  24. ArGuard Shared Task: Harmful Content Detection in Arabic Memes and LLM Prompts

    Sep 24, 2026Firoj Alam, Md. Rafiul Biswas, Mohamed Bayan Kmainasi +5Hate Speech DetectionMemes

    Qatar Computing Research Institute, Qatar · Hamad Bin Khalifa University, Qatar · APAVI.AI, France +1

  25. Baszta: Data-Centric Fine-Tuning of a Polish Multi-Label Safety Classifier

    Sep 24, 2026Adam Górski, Mateusz Jąkalak, Rafał JakubowskiLarge Language Model SafetyClassifier

    Billennium S.A.

  26. Harm Laundering in GPT Models: Evidence That Gender Discrimination Is Transformed Rather Than Reduced Across Safety-Trained Generations

    Sep 17, 2026Sarah Wyer, Sue Black, Noura Al MoubayedToxicityLarge Language Model Safety

    Durham University

  27. Xeno-Interpretability: Investigating the Alien Minds of LLMs

    Sep 17, 2026F. Pierucci, M. Bracale Syrnikov, M. Prandi +3Large Language Model Safety

    Icaro Foundation · Sant’Anna School of Advanced Studies · University of Amsterdam +1

  28. Local Sparsity Enables Unsupervised LLM Safety Detection

    Sep 17, 2026Xin Chen, Gil Kur, Alexander Shevchenko +1Large Language Model SafetySparsity

    ETH Zürich

  29. From Intent to Action: Benchmarking LLM Safety in Vehicle Voice Command Authorization

    Sep 17, 2026Diba Afroze, Xingli Zhang, Yazhou Tu +1Large Language Model SafetyLarge Language Model Decisions

    University of Louisiana at Lafayette, Lafayette, LA 70503, USA · Auburn University, Auburn, AL 36849, USA

  30. Safety Beyond the Interface: Detecting Harm via Latent States in Large Language Models

    Sep 16, 2026Alizishaan Khatri, Chiquita Prabhu, Omkar NeogiLarge Language Model SafetyGuardrail

    Wrynx Inc. · Independent Researcher

  31. The Role of Fine-grained Harm Signals in LLM Safety

    Sep 16, 2026Soyeon Park, Seogyeong Jeong, Sunwoo Kim +1Large Language Model SafetyHarmful Content

    KAIST

  32. Beyond Routine Compliance: Cunning Data Cultivates Safety Vigilance in Large Language Models

    Sep 16, 2026Youjia Wang, Lin Xu, Yang Sun +3Large Language Model SafetyJailbreak Attacks

    Huawei Technology Inc

  33. First Token Matters: Understanding Safety Collapse in Large Reasoning Models

    Sep 16, 2026Yizheng Yang, Haining Yu, Yuechen Wang +4Large Language Model SafetyLarge Reasoning Models

    Harbin Institute of Technology, Harbin, China · Guangzhou University, Guangzhou, China · City University of Macau, Macau, China

  34. Inoculation Midtraining with Learned Neologisms

    Sep 14, 2026Kyle O'Brien, Edward James Young, Puria Radmard +4Large Language Model SafetyInoculation Prompting

    Geodesic Research · OpenAI · UK AI Security Institute

  35. K-Bench: a clinically calibrated benchmark for evaluating large language models in high-risk mental health conversations

    Sep 14, 2026Laura M. Vowels, Matthew J. Vowels, Shivali Sharma +9Large Language Model SafetyMental Health

    School of Psychology, University of Roehampton, London, United Kingdom · Kivira Health, United Kingdom · University of Hertfordshire, Hatfield, United Kingdom +4

  36. Divide, Consult, Conquer: Capability Laundering Through Aligned LLMs

    Sep 14, 2026Mark Russinovich, Blake Bullwinkel, Giorgio Severi +2Large Language Model SafetyStrong Large Language Model

    Microsoft Azure · Microsoft

  37. SIRF: A Spec-Internalized Risk Foundation Model for Industrial Content Risk Control

    Sep 12, 2026Suwan Wu, Yumeng Lin, Pengcheng Yuan +1Conformal Risk ControlArtificial Intelligence Risk

    Xiaohongshu Inc. · Tianjin University

  38. An Efficient and Modular Framework for Targeted Harm Mitigation in LLMS

    Sep 12, 2026Roberto Campbell, Momin Abbass, Muneeza Azmat +5Large Language Model SafetyLarge Language Model Alignment

    University of California, Santa Cruz · IBM Research

  39. RAG-Safety-Bench: Reliable Evaluation of Retrieval-Augmented LLM Safety

    Sep 11, 2026Adithiyan Rajan Indira Saravanan, Kathleen C. FraserLarge Language Model SafetyAgentic Retrieval-Augmented Generation Systems

    Faculty of Engineering University of Ottawa Ottawa, Canada

  40. Arbitrary Cipher Attacks Against Large Language Models Do Not Require Fine-Tuning

    Sep 10, 2026Thomas RivasseauLarge Language Model JailbreaksLarge Language Model Safety

    School of Information Studies McGill University

  41. CS-Guard: Benchmarking LLM Guardrails for Code Generation Security

    Sep 9, 2026Jinyang Li, Mingyu Guo, Hung X. NguyenLarge Language Model SafetyCode Generation

    Adelaide University Adelaide, Australia

  42. Benchmark Scores Are Pipeline-Dependent: A Reliability Audit of Cybersecurity LLM Benchmarks

    Sep 8, 2026Aymene Berriche, Cathrine Shalby, Mohannad Alhanahnah +1Large Language Model SafetyCybersecurity

    Qatar Computing Research Institute, HBKU

  43. Style Over Substance: Content-Invariant Wrappers Flip LLM Safety-Judge Verdicts

    Sep 8, 2026Yongxi Zhou, Wenbo Ye, Yuanzhe Liu +2Large Language Model SafetyJailbreak Success Rates

    Northeastern University, Massachusetts, USA · University of Southern California, California, USA · Georgia Institute of Technology, Georgia, USA

  44. Risk-Conditioned Fine-Tuning of Large Language Models

    Sep 8, 2026Zixuan Liu, Fangzheng Wu, Brian Summa +1Large Language Model SafetyReinforcement Learning From Human Feedback

    Department of Computer Science, Tulane University, New Orleans, LA, 70118, USA

  45. SAFIRE: Safety-Critical Benchmark for Fine-grained Fire and Smoke Understanding in Multimodal LLMs

    Sep 7, 2026Pengfei Li, Naufal Suryanto, Sicheng Zhang +2Multimodal Large Language ModelsLarge Language Model Safety

    Khalifa University · University of Western Australia

  46. LLM Forensics: Where Do Backdoors Hide? Localizing and Controlling Trigger Mechanisms with Sparse Autoencoders

    Sep 7, 2026Wissam Antoun, Francis Kulumba, Théo Lasnier +2Large Language Model SafetyContinuation

    Inria Paris

  47. The Oversight Gap: What LLM Safety Monitors Miss, and Why It Is Not Capability

    Sep 7, 2026Xin XuScalable OversightLarge Language Model Safety

    Carnegie Mellon University

  48. Mitigating LLM Over-Refusal via Dynamic Semantic Routing Calibration

    Sep 6, 2026Zixuan Wang, Bingjie Zhang, He Zhao +1Large Language Model SafetyRefusals

    School of Artificial Intelligence, Jilin University · CSIRO, Australia · Center of Excellence for Generative AI, King Abdullah University of Science and Technology

  49. Recall Is Not Protection: Evaluating Safety Monitors Against Model Compliance

    Sep 5, 2026Sripad KarneLarge Language Model SafetyFalse-Negative Rate

    Columbia University

  50. Representational alignment yields generalizable safety in language models

    Sep 3, 2026Lingyu Li, Yan Teng, Yingchun Wang +1Large Language Model SafetyLarge Language Model Alignment

    Shanghai Artificial Intelligence Laboratory, Shanghai, China

  51. IndicSafeEval: Safety Robustness of Large Language Models under Multilingual Persuasive Jailbreak Attacks

    Sep 3, 2026Saikat Mondal, Mamta, Deeksha Varshney +2Large Language Model SafetyLarge Language Model Evaluation

    Indian Institute of Technology Jodhpur, Jodhpur, India · King’s College London, London, UK · Indian Institute of Technology Patna, Patna, India

  52. SDARE-Bench: Evaluating Large Language Models on Conversational Stigma Detection and Response in Dyadic and Group Dialogue

    Sep 1, 2026Stephanie Fong, Yiwen Jiang, Zimu Wang +12Large Language Model Safety

    Monash University · University of Liverpool · University of Edinburgh +2

  53. Same Request, Different Boundary: Evaluating Cybersecurity Assistance across Conversational Contexts

    Sep 1, 2026Rui Yang, Yang Hong, Yichao Xu +3Large Language Model SafetyCybersecurity

    Johns Hopkins University

  54. The Safeguard Worked. Is the LLM System Safer?

    Sep 1, 2026Pingyu Wu, Weiming Zhang, Nenghai YuLarge Language Model SafetySafer

    University of Science and Technology of China · 2Hefei AiDA Lab

  55. Beyond Token Positions: Safety Alignment Across Denoising Steps in Diffusion Language Models

    Aug 31, 2026Guoli Wang, Haonan Shi, Tu Ouyang +1Diffusion Language ModelsLarge Language Model Safety

    Case Western Reserve University 10900 Euclid Avenue, Cleveland, OH 44106, USA

  56. Capability-Gated Language Models: Security Composes, Utility Does Not

    Aug 31, 2026Patrikas Vanagas, Augustas Mačijauskas, Laurynas LopataLarge Language Model SafetyAccess Control

    BPTI Vilnius, Lithuania · Independent Researcher Vilnius, Lithuania · askEarth AG Zürich, Switzerland

  57. Distributed Implicit Harm: A Compositional Safety Blind Spot in MLLM-Based Video Moderation

    Aug 31, 2026Ruotong Wang, Zihao Zhu, Siwei Lyu +2Video Multimodal Large Language ModelsMultimodal Large Language Models

    The Chinese University of Hong Kong, Shenzhen · Kling Team, Kuaishou Technology · State University of New York at Buffalo

  58. SingProbe Technical Report

    Aug 31, 2026Sing TeamLarge Language Model SafetyRuntime Safety Filtering

    AI Security Lab, Ant Group

  59. Interpreting and Steering for Safe and Correct Code Generation

    Aug 30, 2026Hao Yan, Ziyu YaoLarge Language Model SafetyVulnerable Code

    Department of Computer Science George Mason University, Fairfax, VA

  60. When Safety Speaks a Language: A Mechanistic Analysis of Safety-Language Identity Entanglement in LLMs

    Aug 30, 2026Apoorva Upadhyaya, Sandipan SikdarMultilingual SafetyLarge Language Model Safety

    L3S Research Center, Leibniz Universität Hannover, Germany