LLM Safety

LLM: Large Language Model

LLM safety studies how models can avoid harmful assistance, manipulation, privacy violations, and unreliable advice while still helping with legitimate requests. Approaches include safety training and data filtering, inference-time guardrails and steering, output monitoring, and mechanistic methods that probe or edit internal representations. Benchmarks increasingly test jailbreaks across languages and modalities, long conversations, tool use, and high-stakes settings such as health and cybersecurity. A central challenge is maintaining robustness against adaptive attacks and changing contexts without causing over-refusal or sacrificing utility.

Latest papers

442 papers68 papers in the last four weeks, up 70% on the four weeks before. 0.4% of all new papers.

TWGuard: A Case Study of LLM Safety Guardrails for Localized Linguistic Contexts
Apr 17, 2026Hua-Rong Chu, Kuan-Chun Wang, Yao-Te HuangLanguage Model Safety Evaluation LLM Guardrails
Chunghwa Telecom Laboratories
FineSteer: A Unified Framework for Fine-Grained Inference-Time Steering in Large Language Models
Apr 16, 2026Zixuan Weng, Jinghuai Zhang, Kunlin Cai +3Language Model Steering LLM Safety
University of California, Los Angeles
Segment-Level Coherence for Robust Harmful Intent Probing in LLMs
Apr 16, 2026Xuanli He, Bilgehan Sel, Faizan Ali +3LLM Safety LLM Jailbreak Attacks
University College London · Virginia Tech · Anthropic
Bounded Autonomy for Enterprise AI: Typed Action Contracts and Consumer-Side Execution
Apr 16, 2026Sarmad Sohail, Ghufran HaiderLLM Guardrails AI Agent Security
CausalDetox: Causal Head Selection and Intervention for Language Model Detoxification
Apr 16, 2026Yian Wang, Yuen Chen, Agam Goyal +1Causal Reasoning in Language Models LLM Safety
Department of Computer Science University of Illinois, Urbana-Champaign Champaign, IL 61801
A Multi-Domain Red Teaming Framework for Safety, Robustness, and Fairness Evaluation of Medical Large Language Models
Apr 15, 2026Andrei Marian Feier, Veysel Kocaman, Yigit Gul +6LLM Safety LLM Safety Evaluation
John Snow Labs Inc.
HazardArena: Evaluating Semantic Safety in Vision-Language-Action Models
Apr 14, 2026Zixing Chen, Yifeng Gao, Li Wang +8Robotics AI Safety Evaluation
Fudan University · City University of Hong Kong · Shanghai Innovation Institute
Preventing Safety Drift in Large Language Models via Coupled Weight and Activation Constraints
Apr 14, 2026Songping Peng, Zhiheng Zhang, Daojian Zeng +2Safety-Preserving Fine-Tuning of Language Models LLM Safety Alignment
Hunan Normal University · University of Chinese Academy of Sciences · The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences +1
Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy Backdoors
Apr 14, 2026Rui Yin, Tianxu Han, Naen Xu +8LLM Backdoor Attacks Language Model Editing
Zhejiang University · Palo Alto Networks · OPPO Research Institute +2
Why Do Large Language Models Generate Harmful Content?
Apr 13, 2026Rajesh Ganguli, Raha MoraffahLLM Safety LLM Interpretability
Worcester Polytechnic Institute
Persona Non Grata: Single-Method Safety Evaluation Is Incomplete for Persona-Imbued LLMs
Apr 13, 2026Wenkai Li, Fan Yang, Shaunak A. Mehta +1Language Model Safety Evaluation LLM Safety
Carnegie Mellon University · Fujitsu Research of America Inc.
Jailbreaking the Matrix: Nullspace Steering for Controlled Model Subversion
Apr 11, 2026Vishal Pramanik, Maisha Maliha, Susmit Jha +1Adversarial Attacks on LLMs LLM Jailbreak Attacks
Department of Computer & Information Science & Engineering, University of Florida, Gainesville, FL 32611, USA · School of Computer Science, University of Oklahoma, Norman, OK 73019, USA · Computer Science Laboratory, SRI International, Menlo Park, CA 94025, USA
Large Language Models Generate Harmful Responses Using a Distinct Mechanism, Shared Across Harm Types
Apr 10, 2026Hadas Orgad, Boyi Wei, Kaden Zheng +4LLM Alignment Emergent Misalignment in Language Models
Kempner Institute, Harvard University · Princeton University · Harvard University +2
Conflicts Make Large Reasoning Models Vulnerable to Attacks
Apr 10, 2026Honghao Liu, Chengjin Xu, Xuhui Jiang +5LLM Safety Large Reasoning Models
International Digital Economy Academy · The Hong Kong University of Science and Technology (Guangzhou) · DataArc Tech +1
Silencing the Guardrails: Inference-Time Jailbreaking via Dynamic Contextual Representation Ablation
Apr 9, 2026Wenpeng Xing, Moran Fang, Guangtai Wang +2Adversarial Attacks on LLMs Jailbreak Attacks
Zhejiang University · Binjiang Institute of Zhejiang University
Exclusive Unlearning
Apr 7, 2026Mutsumi Sasaki, Kouta Nakayama, Yusuke Miyao +2LLM Unlearning LLM Safety
Tohoku University · NII LLMC · The University of Tokyo
CareGuardAI: Context-Aware Multi-Agent Guardrails for Clinical Safety & Hallucination Mitigation in Patient-Facing LLMs
Apr 7, 2026Elham Nasarian, Abhilash Neog, Kwok-Leung Tsui +1LLM Guardrails LLM Safety
Grado Department of Industrial & Systems Engineering, Virginia Tech, Blacksburg, VA 24061, USA · Department of Computer Science, Virginia Tech, Blacksburg, VA 24061, USA · Dept of Industrial, Manufacturing, and Systems Engineering at University of Texas at Arlington, Arlington, TX 76019, USA
The Role of Emotional Stimuli and Intensity in Shaping Large Language Model Behavior
Apr 7, 2026Ameen Patel, Felix Lee, Kyle Liang +1LLM Prompting LLM Safety
Irvington High School · Glen A. Wilson High School · Del Norte High School +1
From Retinal Evidence to Safe Decisions: RETINA-SAFE and ECRT for Hallucination Risk Triage in Medical LLMs
Apr 7, 2026Zhe Yu, Wenpeng Xing, Meng HanHallucination Detection LLM Hallucination Detection
Binjiang Institute of Zhejiang University, Hangzhou, China · Communication University of Zhejiang, Hangzhou, China · Zhejiang University, Hangzhou, China
Gradient-Controlled Decoding: A Safety Guardrail for LLMs with Dual-Anchor Steering
Apr 6, 2026Purva Chiniya, Kevin Scaria, Sagar ChaturvediLLM Guardrails LLM Safety
Amazon Alexa · Amazon AGI
Do No Harm: Exposing Hidden Vulnerabilities of LLMs via Persona-based Client Simulation Attack in Psychological Counseling
Apr 6, 2026Qingyang Xu, Yaling Shen, Stephanie Fong +7LLM Safety Adversarial Attacks on LLMs
Monash University · University of Liverpool
How Alignment Routes: Localizing, Scaling, and Controlling Policy Circuits in Language Models
Apr 6, 2026Gregory N. FrankLLM Interpretability LLM Safety
Chief Scientist, Molt AI Corp.
Shorter, but Still Trustworthy? An Empirical Study of Chain-of-Thought Compression
Apr 5, 2026Lingjie Zeng, Xiaofan Chen, Yanbo Wang +1CoT Compression LLM Compression
Mohamed bin Zayed University of Artificial Intelligence
The Silicon Mirror: Dynamic Behavioral Gating for Anti-Sycophancy in LLM Agents
Apr 1, 2026Harshee Jignesh ShahLLM Sycophancy LLM Safety
Independent Researcher
Trojan-Speak: Bypassing Constitutional Classifiers with No Jailbreak Tax via Adversarial Finetuning
Mar 30, 2026Bilgehan Sel, Xuanli He, Alwin Peng +2Adversarial Attacks on LLMs LLM Safety
Anthropic Fellows Program · Virginia Tech · University College London, UK +1
Information-Theoretic Limits of Safety Verification for Self-Improving Systems
Mar 30, 2026Arsenios ScrivensLLM Safety Neural Network Verification
Over-Refusal and Representation Subspaces: A Mechanistic Analysis of Task-Conditioned Refusal in Aligned LLMs
Mar 29, 2026Utsav Maskey, Mark Dras, Usman NaseemLLM Interpretability LLM Refusal Behavior
Macquarie University
GUARD-SLM: Token Activation-Based Defense Against Jailbreak Attacks for Small Language Models
Mar 28, 2026Md Jueal Mia, Joaquin Molto, Yanzhao Wu +1Jailbreak Defense Jailbreak Detection
Knight Foundation School of Computing and Information Sciences Florida International University Miami, FL, USA · Security, Optimization, and Learning for InterDependent networks laboratory (solid lab) Florida International University Miami, FL, USA
Beyond Content Safety: Real-Time Monitoring for Reasoning Vulnerabilities in Large Language Models
Mar 26, 2026Xunguang Wang, Yuguang Zhou, Qingyue Wang +5LLM Safety Monitoring LLM Safety
The Hong Kong University of Science and Technology, Hong Kong, China · Zhejiang University of Technology, Hangzhou, Zhejiang Province, China
When Understanding Becomes a Risk: Authenticity and Safety Risks in the Emerging Image Generation Paradigm
Mar 25, 2026Ye Leng, Junjie Chu, Mingjie Li +5MLLM Safety Image Generation
CISPA Helmholtz Center for Information Security · Xi’an Jiaotong University · Flexera

Apr 17, 2026J/K move · Enter open · S save

TWGuard: A Case Study of LLM Safety Guardrails for Localized Linguistic Contexts

Hua-Rong Chu, Kuan-Chun Wang, Yao-Te Huang

Chunghwa Telecom Laboratories

Language Model Safety Evaluation LLM Guardrails LLM Safety

Open paper AskPDF arXiv

Safety guardrails have become an active area of research in AI safety, aimed at ensuring the appropriate behavior of large language models (LLMs). However, existing research lacks consideration of nuances across linguistic and cultural contexts, resulting in a gap between reported performance and in-the-wild effectiveness. To address this issue, this paper proposes an approach to optimize guardrail models for a designated linguistic context by leveraging a curated dataset tailored to local linguistic characteristics, targeting the Taiwan linguistic context as a representative example of localized deployment challenges. The proposed approach yields TWGuard, a linguistic context-optimized guardrail model that achieves a huge gain (+0.289 in F1) compared to the foundation model and significantly outperforms the strongest baseline in practical use (-0.037 in false positive rate, a 94.9% reduction). Together, this work lays a foundation for regional communities to establish AI safety standards grounded in their own linguistic contexts, rather than accepting boundaries imposed by dominant languages. The inadequacy of the latter is reconfirmed by our findings.