Large Language Model Safety

Follow this field Ask about this field

Recent momentum

emerging

0 papers in the last 28 days · 0.0% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this field, kept on the site without email delivery.

Period ending 2026-09-21

27 new papers

A weekly snapshot of new work published in Large Language Model Safety.

Period ending 2026-09-14

12 new papers

A weekly snapshot of new work published in Large Language Model Safety.

Inside this field

Focused directions

Focused topic

Large Language Model Safety

Within Large Language Model Safety

532 papersExplore

Focused topic

Language Model Evasion Attacks

Within Large Language Model Safety

204 papersExplore

Focused topic

Adversarial Evaluation

Within Large Language Model Safety

114 papersExplore

Focused topic

Adversarial Prompting

Within Large Language Model Safety

30 papersExplore

855 papers

Latest in Large Language Model Safety

Browse all topics →

SafeMed-R1: Clinician-Audited Safety and Ethics Alignment for Medical Large Language Models
May 27, 2026Chao Ding, Mouxiao Bian, Tianbin Li +12Large Language Model Safety Safety
Plant, Persist, Trigger: Sleeper Attack on Large Language Model Agents
May 27, 2026Yongxiang Li, Moxin Li, Zhixin Ma +4Language Model Evasion Attacks Large Language Model Agents
No Safe Dose: How Training Data Drives Unsafe Image Generation
May 27, 2026Felix Friedrich, Lukas Helff, Niharika Hegde +2Text-To-Image Large Language Model Safety
SilentRetrieval: Hijacking Retrieval-Augmented Generation via Semantically-Preserving Adversarial Data Poisoning
May 27, 2026Jiachen QianRetrieval-Augmented Generation Systems Language Model Evasion Attacks
SPARD: Defending Harmful Fine-Tuning Attack via Safety Projection with Relevance-Diversity Data Selection
May 27, 2026Shuhao Chen, Weisen Jiang, Yeqi Gong +5Harmful Fine-Tuning Model-Agnostic Defense
KSAFE-MM: A Multimodal Safety Benchmark via Localized Contextualization for Korean Cultural Risks
May 27, 2026Yongwoo Kim, Sojung An, Yunjin Park +8Large Language Model Safety Safeguard
Where Does Toxicity Live? Mechanistic Localization and Targeted Suppression in Language Models
May 27, 2026Himanshu Beniwal, Mayank SinghToxicity Large Language Model Safety
Pressure-Testing Deception Probes in LLMs: Scaling, Robustness, and the Geometry of Deceptive Representations
May 27, 2026Sachin KumarDeception Language Model Evasion Attacks
SuiChat-CN: Benchmarking Contextual Suicide Risk Assessment in Chinese Group Chats
May 27, 2026Xiangyu Wang, Zhiwei Yu, Chengze Du +3Suicide Risk Social Media
The Fragility of Chain-of-Thought Monitoring Across Typologically Diverse Languages
May 27, 2026Eric Onyame, Runtao Zhou, Kowshik Thopalli +2Adversarial Evaluation Chain-of-Thought Reasoning
When Context Flips, Safety Breaks: Diagnosing Brittle Safety in Aligned Language Models
May 27, 2026Dasol Choi, Alex KwonLarge Language Model Safety Fragility
Disentangling Adversarial Prompts: A Semantic-Graph Defense for Robust LLM Security
May 27, 2026Xiang Fang, Wanlong FangAdversarial Prompting Large Language Model Safety
A Paired Testing Protocol for Batch-Conditioned Refusal Robustness in LLM Serving
May 26, 2026Sahil KadadekarLarge Language Model Safety Refusals
TRACES: Proactive Safety Auditing for Multi-Turn LLM Agents via Trajectory-State Modeling
May 26, 2026Jiaqian Li, Yanshu Li, Boxuan Zhang +2Large Language Model Safety Safety
Evolving and Detecting Multi-Turn Deception using Geometric Signatures
May 26, 2026Surender Suresh Kumar, Mary L. CummingsDeception Large Language Model Safety
Poison with Style: A Practical Poisoning Attack on Code Large Language Models
May 26, 2026Khang Tran, Yazan Boshmaf, Issa Khalil +3Language Model Evasion Attacks Data Poisoning
FinHarness: An Inline Lifecycle Safety Harness for Finance LLM Agents
May 26, 2026Haoxuan Jia, Yang Liu, Bin Chong +10Personalized Large Language Model Agents Finance Domain
When Medical Safety Alignment Fails: A Benchmark for Evaluating LLMs on High-Risk Medical Queries
May 26, 2026Yige Li, Jun Sun, Wei Zhao +5Large Language Model Safety Stress Testing
Learning to Orchestrate Agents under Uncertainty
May 26, 2026Mary Chriselda Antony Oliver, Lan Jiang, Aaron Bundi Anampiu +3Multi-Agent Orchestration Frameworks Orchestration
Prompt Injection Detection is Regime-Dependent: A Deployment-Aware Evaluation with Interpretable Structural Signals
May 26, 2026Akindoyin Akinrele, Shreyank N GowdaIndirect Prompt Injection Large Language Model Safety
AlbanianLLMSafety: A Safety Evaluation Dataset for Large Language Models in Albanian
May 26, 2026Wajdi Zaghouani, Kholoud K. Aldous, Isra FejzullajLarge Language Model Safety Low-Resource Languages
KZ-SafetyPrompts: A Kazakh Safety Evaluation Prompt Dataset for Large Language Models
May 26, 2026Wajdi Zaghouani, Shimaa Amer Ibrahim, Aruzhan Muratbek +2Large Language Model Safety Safety Evaluation
Cordyceps: Covert Control Attacks on LLMs via Data Poisoning
May 26, 2026Zedian Shao, Charles Fleming, Teodora BalutaLanguage Model Evasion Attacks Data Poisoning
SEC-bench Pro: Can Language Models Solve Long-Horizon Software Security Tasks?
May 26, 2026Hwiwon Lee, Jiawei Liu, Dongjun Kim +3Vulnerability Detection & Repair Large Language Model Safety
Open-Weight LLM Fine-Tuning Defenses are Susceptible to Simple Attacks
May 26, 2026Kevin Kuo, Chhavi Yadav, Virginia SmithLanguage Model Evasion Attacks Adversarial Jailbreaks
Model Unlearning Objectives Vary for Distinct Language Functions
May 26, 2026Berk Atil, Vipul Gupta, Rebecca J. PassonneauLarge Language Model Unlearning Large Language Model Safety
Erased but Exploitable: Black-box Embedding-Aware Prompting Against Unlearned Text-to-Image Diffusion Models
May 25, 2026Arian Komaei Koma, Seyed Amir Kasaei, AmirMahdi Sadeghzadeh +1Text-To-Image Diffusion Models Adversarial Prompting
SafeCtrl-RL: Inference-Time Adaptive Behaviour Control for LLM Dialogue via RL-Driven Prompt Optimisation
May 25, 2026Michael Orme, Yanchao Yu, Zhiyuan TanLarge Language Model Safety Multi-Turn Large Language Model Conversations
$D^2$ -Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing
May 25, 2026Aoxi Liu, Yupeng Chen, James Oldfield +5Large Language Model Safety Harmful Content
StructBreak: Structural Cognitive Overload-Induced Safety Failures in MLLMs
May 25, 2026Yang Luo, Xinran Liu, Tiantian Ji +3Large Language Model Safety Multi-Modal Large Language Models
The Age of Curiosity Meets the Age of AI: Benchmarking Child Safety in Large Language Models
May 25, 2026Samee Arif, Angana Borah, Rada MihalceaLarge Language Model Safety Age
SomaliBench Eval: Measuring English-to-Somali Refusal Gaps in Open-Weight Language Models
May 25, 2026Khalid Yusuf DahirLarge Language Model Safety Low-Resource Languages
Evo-Attacker: Memory-Augmented Reinforcement Learning for Long-Horizon Tool Attacks on LLM-MAS
May 25, 2026Bingyu Yan, Xiaoming Zhang, Jinyu Hou +4Language Model Evasion Attacks Transferable Attack
Device Context Protocol: A Compact, Safety-First Architecture for LLM-Driven Control of Constrained Devices
May 24, 2026Dongxu YangResource-Constrained Edge Devices Large Language Model Safety
Furina: Fragmented Uncertainty-Driven Refusal Instability Attack
May 24, 2026Tongxi Wu, Jian Zhang, Yang GaoLarge Language Model Safety Large Language Model Uncertainty
Inverting the Shield: Systematically Generating Safety Tests from Policy Specifications
May 24, 2026Xiaoyue Lu, Xianglin Yang, Haijun Liu +4Large Language Model Safety Artificial Intelligence Safety
Turning Bias into Bugs: Bandit-Guided Style Manipulation Attacks on LLM Judges
May 24, 2026Xianglin Yang, Bryan Hooi, Gelei Deng +2Language Model Evasion Attacks Llm-As-A-Judge
Reflect-Guard: Enhancing LLM Safeguards against Adversarial Prompts via Logical Self-Reflection
May 24, 2026Lixing Lin, Juli You, Yue Li +4Large Language Model Safety Guard
RouteScan: A Non-Intrusive Approach to Auditing MoE LLMs Safety via Expert Routing Telemetry
May 24, 2026Bo Lv, Zhiheng Xu, KeDong Xiu +4Large Language Model Safety Mixture-Of-Expert Language Models
CyberMaskQA: A Privacy-Aware Benchmark for Evaluating Large Language Models in Cybersecurity Question Answering
May 23, 2026Matilda Gaddi, Jin Noh, Onat Gungor +1Cybersecurity Large Language Model Safety
Med-R2: An Adversarial Benchmark for Evidence-Grounded Reasoning in Medical VLMs
May 23, 2026Wen Ma, Fucheng Niu, Zhiting Fan +3Medical Visual Question Answering Clinical Reasoning
Poisoning the Watchtower: Prompt Injection Attacks Against LLM-Augmented Security Operations Through Adversarial Log Content
May 23, 2026Rohan Pandey, Archit BhujangLanguage Model Evasion Attacks Hijacking
JT-SAFE-V2: Safety-by-Design Foundation Model with World-Context Data
May 23, 2026Junlan Feng, Fanyu Meng, Chong Long +12Large Language Model Safety Wireless Foundation Models
Enhancing Reliability in LLM-Based Secure Code Generation
May 22, 2026Mohammed F. Kharma, Mohammad Alkhanafseh, Ahmed Sabbah +1Large Language Model Safety Code Generation
An Empirical Evaluation of LLM-Generated Code Security Across Prompting Methods
May 22, 2026Mohammed Kharma, Ahmed Sabbah, Mohammad Alkhanafseh +2Code Generation Large Language Model Safety
Safety-Oriented Routing Analysis of Mixtral MoE Under Benign and Harmful Prompts
May 22, 2026Md Nurul Absar SiddikyMixture-Of-Expert Language Models Large Language Model Routing
ProofAgent Harness: Open Infrastructure for Adversarial Evaluation of AI Agents
May 22, 2026Fouad BousetouaneAgentic Evaluations Adversarial Evaluation
MemAudit: Post-hoc Auditing of Poisoned Agent Memory via Causal Attribution and Structural Anomaly Detection
May 22, 2026Zhewen Tan, Yilun Yao, Huiyan Jin +9Language Model Evasion Attacks Algorithm Auditing
When the Manual Lies: A Realistic Benchmark to Evaluate MCP Poisoning Attacks for LLM Agents
May 22, 2026Shi Liu, Xuehai Tang, Xikang Yang +4Language Model Evasion Attacks Data Poisoning
WMAttack: Automated Attack Search for Adversarial Evaluation of World-Model Agents
May 22, 2026Zhixiang Guo, Siyuan Liang, Shi Fu +4Adversarial Evaluation World Models
PoisonForge: Task-Level Targeted Poisoning Benchmark for Instruction-Tuned LLMs
May 22, 2026Luze Sun, Anshuman Suri, Harsh Chaudhari +2Language Model Evasion Attacks Poisoning
Security of LLM-generated Code: A Comparative Analysis
May 21, 2026Srivathsan G Morkonda, Mahmoud Selim, Hala AssalCode Generation Large Language Model Safety
Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety
May 21, 2026Piercosma Bisconti, Matteo Prandi, Federico Pierucci +11Large Language Model Safety Safety Evaluation
Measuring Security Without Fooling Ourselves: Why Benchmarking Agents Is Hard
May 21, 2026Sahar Abdelnabi, Chris Hicks, Konrad Rieck +1Security Analysis Agentic Evaluations
VeriScale: Adversarial Test-Suite Scaling for Verifiable Code Generation
May 21, 2026Yifan Bai, Xiaoyang Liu, Zihao Mou +7Benchmarking Large Language Models Code Generation
On-Policy Consistency Training Improves LLM Safety with Minimal Capability Degradation
May 20, 2026Andy Han, Kristina Fujimoto, Avidan Shah +5Safety Alignment Large Language Model Safety
Latent-space Attacks for Refusal Evasion in Language Models
May 20, 2026Giorgio Piras, Raffaele Mura, Fabio Brau +4Refusals Large Language Model Safety
CR4T: Rewrite-Based Guardrails for Adolescent LLM Safety
May 20, 2026Heajun An, Qi Zhang, Vedanth Achanta +1Large Language Model Safety Guardrail
Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs
May 20, 2026Dylan Feng, Pragya Srivastava, Anca Dragan +1Large Language Model Safety Out-Of-Distribution Detection
LASH: Adaptive Semantic Hybridization for Black-Box Jailbreaking of Large Language Models
May 20, 2026Abdullah Al Nomaan Nafi, Fnu Suya, Swarup Bhunia +1Large Language Model Jailbreaks Adversarial Jailbreaks

May 27, 2026 · cs.AIJ/K move · Enter open · S save

SafeMed-R1: Clinician-Audited Safety and Ethics Alignment for Medical Large Language Models

Chao Ding, Mouxiao Bian, Tianbin Li, Minjia Yuan+11

Shanghai Artificial Intelligence Laboratory, Shanghai, China · Joint Laboratory of Biomedical Artificial Intelligence, Shanghai East Hospital, Tongji University School of Medicine, Shanghai, China · School of Computer Science and Technology, Tongji University, Shanghai, China · University of Washington, Washington, USA · Department of Eye and Vision Sciences, University of Liverpool, Liverpool, United Kingdom

Large language models(LLMs) increasingly match expert performance on licensing examinations, yet routine clinical use remains limited because governance requires auditable reasoning, safety and ethics alignment, and resilience to adversarial misuse. Here we present SafeMed-R1, trained with a traceable Clinical Trust Signals(CTS) pipeline that links each reasoning instance to clinician rubric scores and edit histories, and aligned through safety and ethics supervision and red team stress testing. SafeMed-R1 attains a macro-averaged accuracy of 79.6% across clinical benchmarks. Under adversarial safety testing, it shows the lowest aggregated risk and reduces unsafe outputs by about 3 to 5% relative to its baseline. In a paired expert study of 30 medication safety vignettes, SafeMed-R1 matches PGY1 and PGY2 residents on medical correctness and scores higher for medication safety, guideline consistency, and clinical usefulness. Collectively, these results suggest that clinician-audited supervision provenance, together with domain-tailored safety and ethics alignment, can strengthen governance-relevant evidence without relying on inference-time retrieval or citation grounding.

Large Language Model Safety Safety Safeguard Adversarial Evaluation Ethics

Open paper Ask about it PDF