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. An Empirical Study of Security Calibration in Large Language Models for Code

    Jun 30, 2026Mohammed Latif Siddiq, Md. Nafiu Rahman, Joanna C. S. SantosLarge Language Model SafetyVulnerable Code

  2. SafePyramid: A Hierarchical Benchmark for In-context Policy Guardrailing

    Jun 29, 2026Jiacheng Zhang, Haoyu He, Sen Zhang +5Streaming GuardrailsLarge Language Model Safety

  3. CAREBench: A Child-Safety Risk Benchmark for Language Models

    Jun 29, 2026Kaavya Krishna-Kumar, Elaine Lau, Vaughn Robinson +6Large Language Model SafetyArtificial Intelligence Safety

  4. The Joint Effect of Quantization and Sampling Temperature on LLM Safety Alignment: A Factorial Analysis

    Jun 28, 2026Hari Prasad, Ritam PalLarge Language Model SafetyLarge Language Model Quantization

  5. When Can Conformal Risk Control Certify LLM Outputs? Bounds, Impossibility, and Adaptation for Structured Generation

    Jun 27, 2026Varun KotteConformal Risk ControlLarge Language Model Safety

  6. Cybersecurity is the True Frontier for Generative AI Success or Failure

    Jun 27, 2026Edward Raff, Maor Ashkenazi, Sagar Samtani +2CybersecurityArtificial Intelligence Safety

  7. The Heterogeneous Safety Impacts of Benign Multilingual Fine-Tuning

    Jun 27, 2026Will Hawkins, Kaivalya Rawal, Jonathan Rystrøm +8Multilingual SafetyLarge Language Model Safety

  8. Why Trust Your Agent? Empirical Security Gains from TRiSM-Guided Agentic Workflows in Healthcare

    Jun 27, 2026Liam KearnsAgentic WorkflowsSecurity Analysis

  9. Robust Harmful Features Under Jailbreak Attacks: Mechanistic Evidence from Attention Head Specialization in Large Language Models

    Jun 26, 2026Yanchen Yin, Dongqi Han, Linghui LiJailbreak AttacksLarge Language Model Safety

  10. Yuvion LLM: An Adversarially-Aware Large Language Model for Content And AI Safety

    Jun 26, 2026Ting Ma, Xiufeng Huang, Benlei Cui +43Large Language Model SafetyArtificial Intelligence Safety

  11. Paved with True Intents: Intent-Aware Training Improves LLM Safety Classification Across Training Regimes

    Jun 25, 2026Jeremias Ferrao, Niclas Müller-Hof, Iustin Sîrbu +2Large Language Model SafetyInstruction-Tuned Models

  12. Application of LLMs to Threat Assessment of Foreign Peacekeeping Missions

    Jun 25, 2026Gerhard Backfried, Christian Schmidt, Diego Pilutti +1Large Language Model SafetyThreat Models

  13. RedVox: Safety and Fairness Gaps in Speech Models Across Languages

    Jun 25, 2026Beatrice Savoldi, Sara Papi, Wafa Aissa +2Multilingual SafetyLarge Language Model Safety

  14. Do Safety Guardrails Need to Reason? LeanGuard: A Fast and Light Approach for Robust Moderation

    Jun 25, 2026Dongbin NaGuardrailLarge Language Model Safety

  15. Do Encoders Suffice? A Systematic Comparison of Encoder and Decoder Safety Judges for LLM Adversarial Evaluation

    Jun 24, 2026Han Jeon, Shiv Medler, Joseph Voyles +1Large Language Model SafetyLanguage Model Evasion Attacks

  16. RAS: Measuring LLM Safety Through Refusal Alignment

    Jun 24, 2026Chang-Chieh Huang, Yan-Lun Chen, Chia-Mu Yu +1Large Language Model SafetyLarge Language Model Evaluation

  17. An Approach for a Supporting Multi-LLM System for Automated Certification Based on the German IT-Grundschutz

    Jun 24, 2026Lea Roxanne Muth, Marian MargrafLarge Language Model SafetyGerman

  18. Security and Privacy in Retrieval-Augmented Generation: Architectures, Threats, Defenses, and Future Directions for Building Trustworthy Systems

    Jun 24, 2026Balamurugan Palanisamy, G S S Chalapathi, Vikas Hassija +1Retrieval-Augmented Generation SystemsLarge Language Model Safety

  19. PolicyAlign: Direct Policy-Based Safety Alignment for Large Language Models

    Jun 24, 2026Chang Wu, Junfeng Fang, Houcheng Jiang +5Safety AlignmentLarge Language Model Safety

  20. A Survey of Toxicity Detection and Mitigation Strategies for Multilingual Language Models

    Jun 24, 2026Soham Dan, Himanshu Beniwal, Thomas HartvigsenMultilingual SafetyLarge Language Model Safety

  21. SoK: AI Secure Code Generation: Progress, Pitfalls, and Paths Forward

    Jun 23, 2026Rupam Patir, Keyan Guo, Haipeng Cai +1Code GenerationArtificial Intelligence Safety

  22. Speculative Decoding at Temperature Zero: A Scoped Safety-Invariance Screen with a 48,072-Sample Expansion

    Jun 23, 2026Sahil KadadekarSpeculative DecodingLarge Language Model Safety

  23. One Year Later...The Harms Persist, But So Do We!

    Jun 22, 2026Annika Marie Schoene, Cansu Canca, Gautham Vijay Kumar +1Mental HealthLarge Language Model Safety

  24. Evaluation Awareness Is Not One Capability: Evidence from Open Language Models

    Jun 22, 2026Nilesh Nayan, Aishwarya Sampath Kumar, Rishiraj Girmal +5Safety EvaluationLarge Language Model Safety

  25. SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning

    Jun 22, 2026SingGuard TeamStreaming GuardrailsLarge Language Model Safety

  26. IndicGuard: A Multilingual Safety Guard Model and Dataset for Indic Languages

    Jun 22, 2026Parth Bramhecha, Smit Deshmukh, Sairaj Bodhale +2Multilingual SafetyLarge Language Model Safety

  27. The Geometry of Refusal: Linear Instability in Safety-Aligned LLMs

    Jun 21, 2026Shivam Ratnakar, Kartikeya VatsLarge Language Model SafetyRefusals

  28. AgentLens: Interpretable Safety Steering via Mechanistic Subspaces for Multi-Turn Coding Agent

    Jun 21, 2026Weidi Luo, Qiming Zhang, Yihao Quan +5Large Language Model SafetySafety

  29. Governance Decay: How Context Compaction Silently Erases Safety Constraints in Long-Horizon LLM Agents

    Jun 21, 2026Shiyang ChenLarge Language Model AgentsCompaction

  30. Revelio: Cost-Efficient Agentic Memory Safety Vulnerability Detection For Repository-Scale Codebases

    Jun 20, 2026Yiwei Hou, Hao Wang, Muxi Lyu +6Vulnerability Detection & RepairLarge Language Model Safety

  31. Safe responses matter: Output-aware safety guardrail mitigate over-refusal in MLLMs

    Jun 20, 2026Jiayi Li, Kun ZhanLarge Language Model SafetySafety

  32. Harness-MU: A Safe, Governed, and Effective Harness for Multi-User LLM Agents

    Jun 20, 2026Wangxuan Fan, Xiaoyu Nie, Zhongxiang DaiLarge Language Model AgentsLarge Language Model Safety

  33. CNnotator: LLM-Guided Memory Safety Annotation Synthesis

    Jun 20, 2026Twain Byrnes, Mike DoddsProgram AnalysisLarge Language Model Safety

  34. AOR-Bench: Do Large Audio Language Models Over-Refuse Pseudo-Harmful Queries?

    Jun 19, 2026Jiaxi Yang, Chaewan Chun, Jason Lucas +2Large Audio Language ModelsLarge Language Model Safety

  35. What Do Safety-Aligned LLMs Learn From Mixed Compliance Demonstrations?

    Jun 18, 2026Sihui Dai, Mann PatelLarge Language Model SafetyCompliance

  36. Calibration Without Comprehension: Diagnosing the Limits of Fine-Tuning LLMs for Vulnerability Detection in Systems Software

    Jun 18, 2026Arastoo Zibaeirad, Marco VieiraVulnerability Detection & RepairLarge Language Model Safety

  37. Actionable Activation Directions for Detecting and Mitigating Emergent Misalignment Across Language Model Families

    Jun 18, 2026Abdul Rafay SyedMisalignmentLarge Language Model Alignment

  38. FinRED: An Expert-Guided Benchmark Generation and Evaluation Framework for Financial LLM Red-Teaming

    Jun 18, 2026Chaeyun Kim, Daeyoung Park, Junghwan Kim +4Red-TeamingLarge Language Model Safety

  39. SafeSpec: Fast and Safe LLM via Dynamic Reflective Sampling

    Jun 18, 2026Haotian Xu, Zeyang Zhang, Linbao Li +3Inference-Time DefenseSpeculative Decoding

  40. Analyzing the Narration Gap in LLM-Solver Loops

    Jun 17, 2026Zunchen Huang, Songgaojun DengLarge Language Model SafetyLarge Language Model Reasoning

  41. SciRisk-Bench: A Risk-Dimension-Aware Benchmark for AI4Science Safety

    Jun 17, 2026Linghao Feng, Yinqian Sun, Dongqi Liang +8Large Language Model SafetyBenchmarking Large Language Models

  42. SafeClawBench: Separating Semantic, Audit-Evidence, and Sandbox Harm in Tool-Using LLM Agents

    Jun 16, 2026Yuchuan Tian, Mengyu Zheng, Haocheng Mei +5Large Language Model SafetyFewer Tool-Call Errors

  43. AnchorKV: Safety-Aware KV Cache Compression via Soft Penalty with a Refusal Anchor

    Jun 16, 2026Ning Ni, Yingjie LaoKey-Value Cache CompressionLarge Language Model Safety

  44. Adaptive and Explicit safe: Triggering Latent Safety Awareness in Large Reasoning Models

    Jun 15, 2026Ke Miao, Jiaxin Li, Hongliang Chen +2Large Language Model SafetyLarge Reasoning Models

  45. Tail-Shape Estimation in LLM Evaluation Is Fragile: A Protocol for Diagnosing False Positives

    Jun 15, 2026Luca ZhouLarge Language Model EvaluationLarge Language Model Safety

  46. SPARK: Security Knowledge Priming and Representation-Guided Knowledge Activation for LLM-based Secure Code Generation

    Jun 15, 2026Xiaoyun Xu, Lichao Wu, Jona te Lintelo +2Large Language Model SafetyVulnerable Code

  47. SkillVetBench: LLM-as-Judge for Multi-Dimensional Security Risk Evaluation in Open-Source LLM Agent Skills

    Jun 14, 2026Ismail Hossain, Sai Puppala, Md Jahangir Alam +2Security AnalysisLarge Language Model Safety

  48. Snyk VulnBench JS 1.0: Can LLMs Find the Same Bugs Twice?

    Jun 14, 2026Liran Tal, Johannes Kloos, Arsenii Rudich +2Code QualityVulnerability Detection & Repair

  49. SHARD: Safe and Helpful Alignment via Self-Reframing Distillation

    Jun 14, 2026Viswonathan Manoranjan, Amogh Gupta, Anvesh Rao Vijjini +2Large Language Model SafetyInstruction-Tuned Models

  50. CHILLGuard: Towards Fine-Grained Chinese LLM Safety Guardrail with Scalable Data Construction and Model-aware Preference Alignment

    Jun 13, 2026Wenbo Yu, Bohua Wang, Hao Fang +10Large Language Model SafetySafety

  51. I'm Sorry Driver, I'm Afraid I Can't Do That: Appraising the Safety of LLMs within Automotive Contexts

    Jun 12, 2026Shaun Feakins, Ibrahim Habli, Kim Littler +1Large Language Model SafetyLlm-Driven

  52. Trust but Verify: Mitigating Medical Hallucinations via Post-Hoc Adversarial Auditing and Multi-Agent Feedback Loops

    Jun 12, 2026Muhammad Osama, Maheera Amjad, Zartasha Mustansar +2Large Language Model HallucinationLarge Language Model Safety

  53. Designing Safety-Constrained LLM Systems for Public Health Information Access

    Jun 11, 2026Ben Torkian, Jun ZhouLarge Language Model SafetySafety

  54. FreoStream:Enhancing Stream Guardrails via Future-Aware Reasoning and Safety-Aligned Optimization

    Jun 11, 2026Jianwei Wang, Guoyang Shen, Yanhong Wu +5Streaming GuardrailsLarge Language Model Safety

  55. SafeLLM: Extraction as a Hallucination-Resistant Alternative to Rewriting in Safety-Critical Settings

    Jun 11, 2026Julia Ive, Felix Jozsa, Evridiki Georgaki +6Large Language Model SafetyLarge Language Model Hallucination

  56. The Containment Gap: How Deployed Agentic AI Frameworks Fail Public-Facing Safety Requirements

    Jun 11, 2026Md Jafrin Hossain, Mohammad Arif Hossain, Weiqi Liu +1Large Language Model SafetyModular Agentic Framework

  57. Prefill Awareness in Large Language Models

    Jun 10, 2026Andy Wang, Parv Mahajan, David Demitri Africa +3Large Language Model SafetyFrontier Models

  58. MPC-Patch-Bench: Security-Aware LLM Code Patch for Multi-Party Computation

    Jun 9, 2026Yukuan Zhang, Mengxin Zheng, Qian LouLarge Language Model SafetyProgrambench

  59. Schützen: Evaluating LLM Safety in Bulgarian and German Contexts

    Jun 9, 2026Kiril Georgiev, Yuxia Wang, Dimitar Iliyanov Dimitrov +2Large Language Model SafetyGerman

  60. Stop Early, Spend Less: Hidden-State Probes as a Practical Recipe for Streaming Moderation of LLM Outputs

    Jun 9, 2026Huizhen Shu, Xuying Li, Piao XueLarge Language Model SafetyLarge Language Model Output