LLM Safety

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

36 papers in the last four weeks, up 200% on the four weeks before. 0.4% of all new papers.

Jul 13Week of Sep 28

Latest papers 272

All topics

The Role of Fine-grained Harm Signals in LLM Safety
Sep 16, 2026Soyeon Park, Seogyeong Jeong, Sunwoo Kim +1LLM Interpretability LLM Safety
KAIST
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
Decoy Direction Optimization: A Post-Hoc Defense Against LLM Abliteration
Sep 14, 2026Aashiq Muhamed, Mona T. Diab, Virginia SmithAdversarial Attacks on LLMs LLM Safety
Carnegie Mellon University
Inoculation Midtraining with Learned Neologisms
Sep 14, 2026Kyle O'Brien, Edward James Young, Puria Radmard +4LLM Alignment LLM Safety
Geodesic Research · OpenAI · UK AI Security Institute
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 +9LLM Safety Benchmarks Mental Health Counseling
School of Psychology, University of Roehampton, London, United Kingdom · Kivira Health, United Kingdom · University of Hertfordshire, Hatfield, United Kingdom +4
Beyond Safe Answers: Segment-Aware Listwise Alignment for Reasoning Safety in Large Reasoning Models
Sep 14, 2026JungMin Yun, Junehyoung Kwon, Hayeong Ryu +3LLM Alignment Direct Preference Optimization
Department of Artificial Intelligence, Chung-Ang University · Graduate School of Advanced Imaging Sciences, Multimedia and Film, Chung-Ang University
Semantic Fibers and Cross-Gram Interference: A Calculus of Safety Drift in Overcomplete Representations
Sep 14, 2026Mohammed Ahnouch, Lotfi ElaachackLanguage Model Safety Evaluation LLM Safety
Université Paris 1 Paris, France · Faculty of Science and Technology of Tangier Abdelmalek Essaadi University Tangier, Morocco
SIRF: A Spec-Internalized Risk Foundation Model for Industrial Content Risk Control
Sep 12, 2026Suwan Wu, Yumeng Lin, Pengcheng Yuan +1Content Moderation LLM Safety
Xiaohongshu Inc. · Tianjin University
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
Generative Interpretability via Scalable Neuro-Symbolic Models
Sep 11, 2026Xiaocong YangLLM Interpretability LLM Safety
RAG-Safety-Bench: Reliable Evaluation of Retrieval-Augmented LLM Safety
Sep 11, 2026Adithiyan Rajan Indira Saravanan, Kathleen C. FraserLLM Safety Benchmarks LLM Safety
Faculty of Engineering University of Ottawa Ottawa, Canada
Arbitrary Cipher Attacks Against Large Language Models Do Not Require Fine-Tuning
Sep 10, 2026Thomas RivasseauAdversarial Attacks on LLMs Jailbreak Attacks
School of Information Studies McGill University
Combating Instruction Conflict via Energy-Driven Latent Conflict Detection
Sep 8, 2026Mingyu Ma, Yuxin Wu, Jingbo Wang +3LLM Safety
Wuhan University · Renmin University of China
Risk-Conditioned Fine-Tuning of Large Language Models
Sep 8, 2026Zixuan Liu, Fangzheng Wu, Brian Summa +1Risk-Sensitive RL LLM Safety
Department of Computer Science, Tulane University, New Orleans, LA, 70118, USA
Recall Is Not Protection: Evaluating Safety Monitors Against Model Compliance
Sep 5, 2026Sripad KarneLanguage Model Safety Evaluation LLM Guardrails
Columbia University
IndicSafeEval: Safety Robustness of Large Language Models under Multilingual Persuasive Jailbreak Attacks
Sep 3, 2026Saikat Mondal, Mamta, Deeksha Varshney +2LLM Safety Benchmarks Multilingual Language Model Evaluation
Indian Institute of Technology Jodhpur, Jodhpur, India · King’s College London, London, UK · Indian Institute of Technology Patna, Patna, India
When Retrieval Helps: Selective Retrieval for Single-Turn Mental-Health QA
Sep 3, 2026Hyunseo Oh, Chong-Kwon Kim, Yoonhyuk ChoiRetrieval-Augmented Generation Mental Health Counseling
Sookmyung Women’s University · Korea Institute of Energy Technology
Selective Knowledge Edit Reversal via Gated Singular Vector Shrinkage
Sep 2, 2026Weifeng Jiang, Ruirui Chen, Qianren Mao +3Knowledge Editing LLM Safety
College of Computing and Data Science, Nanyang Technological University, Singapore. · Digital Trust Centre, Nanyang Technological University, Singapore. · Institute of Advanced Intelligence and Computing, Agency for Science, Technology and Research, Singapore. +2
GAPS: Dimension-Level Gates for Conditional Activation Steering
Sep 1, 2026Moghis Fereidouni, Muhammad Umair Haider, Hassan Sajjad +1Language Model Steering LLM Safety
University of Kentucky · Dalhousie University
Same Request, Different Boundary: Evaluating Cybersecurity Assistance across Conversational Contexts
Sep 1, 2026Rui Yang, Yang Hong, Yichao Xu +3LLM Safety Benchmarks LLM Refusal Behavior
Johns Hopkins University
The Safeguard Worked. Is the LLM System Safer?
Sep 1, 2026Pingyu Wu, Weiming Zhang, Nenghai YuLLM Guardrails LLM Safety
University of Science and Technology of China · 2Hefei AiDA Lab
Hidden in the Request: Explaining Unethical LLM Compliance through Token Relevance
Aug 24, 2026Or Biton, Tomer Krichli, Itai Allouche +1Language Model Decoding Language Model Safety Evaluation
Faculty of Electrical and Computer Engineering, Technion, Haifa, Israel
Regime-Conditional Verification: Correctness Estimation for Adapting and Monitoring Safety Classifiers
Aug 14, 2026Thiago Sandoval, Ufuk TopcuDistribution Shift Selective Prediction
The University of Texas at Austin
Beyond Detection: Evaluating Defensive LLMs Against AI-Generated Social Engineering in Live Turn-by-Turn Interaction
Aug 10, 2026Yuqiao Xu, Osama Zafar, Alexander Nemecek +1LLM Safety Benchmarks LLM Safety
Case Western Reserve University
Pragmatic Attack Surface: Vulnerabilities of Implicit Context in Large Language Models
Aug 10, 2026Bocheng Chen, Han Zi, Roucheng Ou +5Pragmatic Reasoning in Language Models Adversarial Attacks on LLMs
University of Mississippi · Indiana University Indianapolis · Michigan State University +1
Who Bridges Safety? Identifying and Targeting Cross-Lingual Shared Safety Pathways
Aug 10, 2026Shuyi Miao, Wangjie Qiu, Pengyang Shao +4LLM Safety Alignment LLM Safety
Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing · School of Artificial Intelligence, Beihang University, China · Zhongguancun Laboratory, Beijing, China +2
HoloAegis: Frozen Representation, Topological Inference --- Minimally Parametric Safety Manifolds and Their Capability Boundaries for LLM Guardrails
Aug 9, 2026Tak Ho Alex Li, Kaijie Liu, Lik-Hang Lee +3Language Model Safety Evaluation LLM Guardrails
Department of Mathematics, Hong Kong Baptist University, Hong Kong 999077 · Guangdong-Hong Kong-Macao Institute of ESG and New Quality Productive Forces, School of Optoelectronic Engineering, Guangdong Polytechnic Normal University, Guangzhou 510665 · Guangdong Institute of Digital Industry, Guangzhou 510000 +3
Yesterday's Shield, Today's Spear: A Self-Evolving Safety Guardrail in Production
Aug 9, 2026Cong Ming, Jingyi Chen, Bin Liu +4Continual Learning for LLMs LLM Guardrails
University of Science and Technology of China · Shenzhen University · Sangfor Technologies
Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning
Aug 5, 2026Yuxuan Huang, Xingyu Zeng, Tianhang Zheng +1LLM Safety Alignment LLM Security
Shanghai Artificial Intelligence Laboratory · Shanghai Jiao Tong University · Shenzhen University of Advanced Technology +1
DelusionEval: Measuring Delusion-Linked Behaviors in AI Chatbots
Aug 5, 2026Jared Moore, Andrea Mock, Yifan Mai +9LLM Safety Benchmarks LLM Safety
Stanford University Stanford, California, USA · University of Chicago Chicago, Illinois, USA · Carnegie Mellon University Pittsburgh, Pennsylvania, USA +2

Sep 16, 2026, cs.CLJ/K move · Enter open · S save

The Role of Fine-grained Harm Signals in LLM Safety

Soyeon Park, Seogyeong Jeong, Sunwoo Kim, Alice Oh

KAIST

LLM Interpretability LLM Safety Refusal Behavior in Language Models

Open paper AskPDF arXiv

Prior work has shown that internal harmfulness representations in large language models vary across risk categories, while sharing a common general harm representation component. This raises a question about the role of the category-specific component beyond general harm representation in LLM safety. To answer this question, we isolate the category-specific component by removing shared general harmfulness representation from each categorical harmfulness representation, yielding a category residual that is orthogonal to general harmfulness at every layer. Using activation steering with category residuals across 11 risk categories in 3 instruction-tuned LLMs, we find that whether category residuals encode harmfulness varies across categories, and that this category-wise pattern is similar across models. Whether category residuals induce refusal also varies across categories, but this category-wise pattern is more model-dependent. We also find that category residuals increase LLMs' downstream internal alignment with shared general harmfulness representation. Together, these findings demonstrate that more fine-grained category residuals should also be considered beyond shared general harmfulness representation to fully understand LLM safety. More broadly, our findings show that even a direction orthogonal to a concept at one layer can contribute to the concept's downstream amplification.

Momentum

Related topics

Latest papers 272