Large Language Model Safety

Ask about this topic

Recent momentum

-47%

39 papers in the last 28 days · 0.6% of indexed attention

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

Also in Large Language Model Safety

Neighbouring directions

Language Model Evasion AttacksAdversarial EvaluationAdversarial Prompting

Weekly history

Recent digests

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

Period ending 2026-09-21

13 new papers

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

Period ending 2026-09-14

11 new papers

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

Period ending 2026-09-07

14 new papers

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

532 papers

Latest in Large Language Model Safety

Browse all topics →
CardsList

  1. Reducing Conversational Escalation in Large Language Model Dialogue with Nonviolent Communication Constraints

    May 1, 2026Zhixing Sun, Shenghe Xu, Tao LiMulti-Turn Large Language Model ConversationsLarge Language Model Safety

  2. FinSafetyBench: Evaluating LLM Safety in Real-World Financial Scenarios

    May 1, 2026Yutao Hou, Yihan Jiang, Yuhan Xie +5Large Language Model SafetyFraud Detection

  3. ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models

    May 1, 2026Yunhan Zhao, Zhaorun Chen, Xingjun Ma +2Multilingual SafetyLarge Language Model Safety

  4. Stable-GFlowNet: Toward Diverse and Robust LLM Red-Teaming via Contrastive Trajectory Balance

    May 1, 2026Minchan Kwon, Sunghyun Baek, Minseo Kim +3Generative Flow NetworksLarge Language Model Safety

  5. Prompt-Induced Score Variance in Zero-Shot Binary Vision-Language Safety Classification

    May 1, 2026Charles Weng, Dingwen Li, Alexander MartinLarge Language Model SafetyLarge Vision Language Models

  6. Jailbroken Frontier Models Retain Their Capabilities

    Apr 30, 2026Daniel Zhu, Zihan Wang, Xuchan Bao +1Novel Jailbreak MethodJailbreaks

  7. ARMOR 2025: A Military-Aligned Benchmark for Evaluating Large Language Model Safety Beyond Civilian Contexts

    Apr 30, 2026Sydney Johns, Heng Jin, Chaoyu Zhang +2Large Language Model SafetyArms

  8. Knowledge Graph Representations for LLM-Based Policy Compliance Reasoning

    Apr 30, 2026Wilder Baldwin, Sepideh GhanavatiKnowledge GraphsArtificial Intelligence Governance

  9. Useless but Safe? Benchmarking Utility Recovery with User Intent Clarification in Multi-Turn Conversations

    Apr 29, 2026Mingqian Zheng, Malia Morgan, Liwei Jiang +2Large Language Model SafetyMulti-Turn Conversations

  10. Dynamic Adversarial Fine-Tuning Reorganizes Refusal Geometry

    Apr 29, 2026Wenhao Lan, Shan Li, Xinhua Lai +4RefusalsLarge Language Model Safety

  11. Benchmarking the Safety of Large Language Models for Robotic Health Attendant Control

    Apr 29, 2026Mahiro Nakao, Kazuhiro TakemotoLarge Language Model SafetySafety

  12. From Prompt Risk to Response Risk: Paired Analysis of Safety Behavior of Large Language Models

    Apr 28, 2026Mengya Hu, Qiong Wei, Sandeep AtluriLarge Language Model SafetyHarms

  13. BARRED: Synthetic Training of Custom Policy Guardrails via Asymmetric Debate

    Apr 28, 2026Arnon Mazza, Elad LeviStreaming GuardrailsSynthetic Training Data

  14. Risk Reporting for Developers' Internal AI Model Use

    Apr 27, 2026Oscar Delaney, Sambhav Maheshwari, Joe O'Brien +2Artificial Intelligence SafetyArtificial Intelligence Governance

  15. Evaluating whether AI models would sabotage AI safety research

    Apr 27, 2026Robert Kirk, Alexandra Souly, Kai Fronsdal +2Artificial Intelligence SafetySabotage

  16. How Sensitive Are Safety Benchmarks to Judge Configuration Choices?

    Apr 27, 2026Xinran ZhangSafety EvaluationLarge Language Model Safety

  17. Ulterior Motives: Detecting Misaligned Reasoning in Continuous Thought Models

    Apr 25, 2026Sharan RamjeeEfficient Latent ReasoningLarge Language Model Safety

  18. AI Safety Training Can be Clinically Harmful

    Apr 25, 2026Suhas BN, Andrew M. Sherrill, Rosa I. Arriaga +2Mental Health SupportLarge Language Model Safety

  19. Semantic Denial of Service in LLM-controlled robots

    Apr 25, 2026Jonathan Steinberg, Oren GalLarge Language Model SafetyMultiple Attack Surfaces

  20. Training a General Purpose Automated Red Teaming Model

    Apr 24, 2026Aishwarya Padmakumar, Leon Derczynski, Traian Rebedea +1Red-TeamingLanguage Model Evasion Attacks

  21. Multilingual Refusal Alignment for Safer Large Language Models

    Apr 24, 2026Aleksandra Krasnodębska, Wojciech Kusa, Aldo LipaniMultilingual SafetyCross-Lingual Alignment

  22. Estimating Tail Risks in Language Model Output Distributions

    Apr 24, 2026Rico Angell, Raghav Singhal, Zachary Horvitz +4Large Language Model Safety

  23. Sovereign Agentic Loops: Decoupling AI Reasoning from Execution in Real-World Systems

    Apr 24, 2026Jun He, Deying YuMulti-Agent Large Language Model SystemsAgent Loop

  24. SHAPE: Unifying Safety, Helpfulness and Pedagogy for Educational LLMs

    Apr 24, 2026Sihang Zhao, Kangrui Yu, Youliang Yuan +2PedagogyTutors

  25. Evaluating Patient Safety Risks in Generative AI: Development and Validation of a FMECA Framework for Generated Clinical Content

    Apr 23, 2026Lydie Bednarczyk, Jamil Zaghir, Julien Ehrsam +11Large Language Model SafetyClinical Notes

  26. CI-Work: Benchmarking Contextual Integrity in Enterprise LLM Agents

    Apr 23, 2026Wenjie Fu, Xiaoting Qin, Jue Zhang +5Data LeakageLarge Language Model Safety

  27. CAP: Controllable Alignment Prompting for Unlearning in LLMs

    Apr 23, 2026Zhaokun Wang, Jinyu Guo, Jingwen Pu +7Large Language Model UnlearningLarge Language Model Alignment

  28. Adaptive Instruction Composition for Automated LLM Red-Teaming

    Apr 22, 2026Jesse Zymet, Andy Luo, Swapnil Shinde +2Red-TeamingLanguage Model Evasion Attacks

  29. Dialect vs Demographics: Quantifying LLM Bias from Implicit Linguistic Signals vs. Explicit User Profiles

    Apr 22, 2026Irti Haq, Belén SaldíasLarge Language Model BiasLarge Language Model Safety

  30. Breaking MCP with Function Hijacking Attacks: Novel Threats for Function Calling and Agentic Models

    Apr 22, 2026Yannis Belkhiter, Giulio Zizzo, Sergio Maffeis +2Language Model Evasion AttacksHijacking

  31. Benchmarking Large Language Models for Safety Data Extraction

    Apr 22, 2026Jonas Grill, Thomas Bayer, Sören BerlingerLarge Language Model SafetyBenchmarking Large Language Models

  32. SafeRedirect: Defeating Internal Safety Collapse via Task-Completion Redirection in Frontier LLMs

    Apr 22, 2026Chao Pan, Yu Wu, Xin YaoLarge Language Model SafetySafeguard

  33. Omission Constraints Decay While Commission Constraints Persist in Long-Context LLM Agents

    Apr 22, 2026Yeran GamageComplianceLarge Language Model Safety

  34. SafetyALFRED: Evaluating Safety-Conscious Planning of Multimodal Large Language Models

    Apr 21, 2026Josue Torres-Fonseca, Naihao Deng, Yinpei Dai +5Large Language Model SafetyAgentic Benchmarks

  35. HarDBench: A Benchmark for Draft-Based Co-Authoring Jailbreak Attacks for Safe Human-LLM Collaborative Writing

    Apr 21, 2026Euntae Kim, Soomin Han, Buru ChangLarge Language Model SafetyAdversarial Jailbreaks

  36. Detoxification for LLM: From Dataset Itself

    Apr 21, 2026Wei Shao, Yihang Wang, Gaoyu Zhu +4DetoxificationToxicity

  37. When Safety Fails Before the Answer: Benchmarking Harmful Behavior Detection in Reasoning Chains

    Apr 21, 2026Ishita Kakkar, Enze Zhang, Rheeya Uppaal +1Reasoning TracesLarge Language Model Safety

  38. STAR-Teaming: A Strategy-Response Multiplex Network Approach to Automated LLM Red Teaming

    Apr 21, 2026MinJae Jung, YongTaek Lim, Chaeyun Kim +3Red-TeamingLanguage Model Evasion Attacks

  39. Harmful Intent as a Geometrically Recoverable Feature of LLM Residual Streams

    Apr 20, 2026Isaac Llorente-SaguerLarge Language Model SafetyInstruction-Tuned Models

  40. LLM Safety From Within: Detecting Harmful Content with Internal Representations

    Apr 20, 2026Difan Jiao, Yilun Liu, Ye Yuan +4Large Language Model SafetyHarmful Content

  41. Using large language models for embodied planning introduces systematic safety risks

    Apr 20, 2026Tao Zhang, Kaixian Qu, Zhibin Li +4Large Language Model PlanningClassical Planning

  42. Owner-Harm: A Missing Threat Model for AI Agent Safety

    Apr 20, 2026Dongcheng Zhang, Yiqing JiangArtificial Intelligence SafetyThreat Models

  43. A Quasi-Experimental Developer Study of Security Training in LLM-Assisted Web Application Development

    Apr 20, 2026Mohammed Kharma, Ahmed Sabbah, Radi Jarrar +3Large Language Model Safety

  44. MHSafeEval: Role-Aware Interaction-Level Evaluation of Mental Health Safety in Large Language Models

    Apr 20, 2026Suhyun Lee, Palakorn Achananuparp, Neemesh Yadav +2Large Language Model SafetyLarge Language Model Evaluation

  45. SafeAgent: A Runtime Protection Architecture for Agentic Systems

    Apr 19, 2026Hailin Liu, Eugene Ilyushin, Jie Ni +1Large Language Model SafetyRuntime Enforcement

  46. Language models recognize dropout and Gaussian noise applied to their activations

    Apr 19, 2026Damiano Fornasiere, Mirko Bronzi, Spencer Kitts +3Model ActivationsTraining Language Models

  47. RoTRAG: Rule of Thumb Reasoning for Conversation Harm Detection with Retrieval-Augmented Generation

    Apr 19, 2026Juhyeon Lee, Wonduk Seo, Junseo Koh +3Large Language Model SafetyMoral Reasoning

  48. Please refuse to answer me! Mitigating Over-Refusal in Large Language Models via Adaptive Contrastive Decoding

    Apr 18, 2026Yupeng Qi, Ziyu Lyu, Lixin Cui +2RefusalsLarge Language Model Safety

  49. When Choices Become Risks: Safety Failures of Large Language Models under Multiple-Choice Constraints

    Apr 18, 2026Yuheng Chen, Zhiyu Wu, Bowen Cheng +1Large Language Model SafetySafety Alignment

  50. DART: Mitigating Harm Drift in Difference-Aware LLMs via Distill-Audit-Repair Training

    Apr 18, 2026Ziwen Pan, Zihan Liang, Jad Kabbara +1Large Language Model SafetyLarge Language

  51. SafeDream: Safety World Model for Proactive Early Jailbreak Detection

    Apr 18, 2026Bo Yan, Weikai Lin, Yada Zhu +1Jailbreak DetectionJailbreak Attacks

  52. HealthCraft: A Reinforcement Learning Safety Environment for Emergency Medicine

    Apr 18, 2026Brandon DentLarge Language Model SafetyEmergency Evacuations

  53. Surgical Repair of Insecure Code Generation in LLMs

    Apr 17, 2026Gustavo Sandoval, Brendan Dolan-Gavitt, Siddharth GargVulnerable CodeVulnerability Detection & Repair

  54. SafeLM: Unified Privacy-Aware Optimization for Trustworthy Federated Large Language Models

    Apr 17, 2026Noor Islam S. Mohammad, Uluğ BayazıtLarge Language Model SafetySafeguard

  55. MCBench: A Multicontext Safety Assessment Benchmark for Omni Large Language Models

    Apr 17, 2026Manh Luong, Tamas Abraham, Junae Kim +6Large Language Model SafetySafety Evaluation

  56. From Consumption to Reflection: Designing Human-AI Relations for Stable Reasoning

    Apr 17, 2026Rikard Rosenbacke, Carl Rosenbacke, Victor Rosenbacke +1Human-Ai InteractionLarge Language Model Reasoning

  57. Pruning Unsafe Tickets: A Resource-Efficient Framework for Safer and More Robust LLMs

    Apr 17, 2026Wai Man Si, Mingjie Li, Michael Backes +1Large Language Model SafetyLarge Language Model Alignment

  58. MemEvoBench: Benchmarking Safety Risks from Memory Misevolution in LLM Agents

    Apr 17, 2026Weiwei Xie, Shaoxiong Guo, Fan Zhang +5Large Language Model SafetyLarge Language Model Agents

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

    Apr 17, 2026Hua-Rong Chu, Kuan-Chun Wang, Yao-Te HuangMultilingual SafetyLarge Language Model Safety

  60. Bounded Autonomy for Enterprise AI: Typed Action Contracts and Consumer-Side Execution

    Apr 16, 2026Sarmad Sohail, Ghufran HaiderEnterprise SystemsLarge Language Model Safety