Language Model Safety Evaluation

Follow this topic Ask about this topic

Language model safety evaluation asks whether models handle harmful, ambiguous, and high-stakes requests safely while still helping with legitimate ones. Researchers use benchmarks such as HarmBench, JailbreakBench, and XSTest, alongside static and adaptive red-teaming, expert review, and automated judges; newer tests also examine multi-turn, tool-using, speech, and multimodal systems. Psychometric methods, repeated sampling, and internal activation probes can reveal risks that single-run refusal scores miss, while localized and domain-specific evaluations test language, culture, and settings such as healthcare or finance. A central challenge is making results reliable and predictive of deployment: robustness can shift with wording, language, interaction length, or evaluator, and reducing harmful compliance can increase over-refusal or undermine useful performance.

Latest papers

550 papers82 papers in the last four weeks, up 64% on the four weeks before. 0.5% of all new papers.

State-Dependent Safety Failures in Multi-Turn Language Model Interaction
Mar 15, 2026Pengcheng Li, Jie Zhang, Tianwei Zhang +5LLM Safety Language Model Safety Evaluation
School of Cyber Science and Technology, University of Science and Technology of China, China · Agency for Science, Technology and Research (A*STAR), Singapore · Nanyang Technological University, Singapore +3
OmniCompliance-100K: A Multi-Domain, Rule-Grounded, Real-World Safety Compliance Dataset
Mar 14, 2026Wenbin Hu, Huihao Jing, Haochen Shi +3Language Model Safety Evaluation LLM Safety Benchmarks
Hong Kong University of Science and Technology · ModeIO
Sell Me This Stock: Unsafe Recommendation Drift in LLM Agents
Mar 13, 2026Zekun Wu, Adriano Koshiyama, Sahan Bulathwela +1LLM Agent Safety Language Model Safety Evaluation
Centre for Artificial Intelligence, University College London · Holistic AI
Understanding LLM Behavior When Encountering User-Supplied Harmful Content in Harmless Tasks
Mar 12, 2026Junjie Chu, Yiting Qu, Ye Leng +4LLM Safety Language Model Safety Evaluation
CISPA Helmholtz Center for Information Security · Flexera · Delft University of Technology
Evaluation format, not only model capability, shapes measured triage failure in consumer health AI
Mar 12, 2026David Fraile Navarro, Jialei Sheng, Farah Magrabi +1Language Model Safety Evaluation LLM Safety Benchmarks
Centre for Health Informatics, Australian Institute of Health Innovation, Macquarie University, Sydney, NSW, Australia · NSW Health, Sydney, NSW, Australia
Systematic Scaling Analysis of Jailbreak Attacks in Large Language Models
Mar 11, 2026Xiangwen Wang, Ananth Balashankar, Varun ChandrasekaranJailbreak Attacks LLM Jailbreak Attacks
University of Illinois Urbana-Champaign · Google DeepMind
Risk-Adjusted Harm Scoring for Automated Red Teaming for LLMs in Financial Services
Mar 11, 2026Fabrizio Dimino, Bhaskarjit Sarmah, Stefano PasqualiLanguage Model Safety Evaluation LLM Safety
1Domyn, New York, US · 2Domyn, New York, US · 3Domyn, New York, US
Evaluating Reliability Gaps in Large Language Model Safety via Repeated Prompt Sampling
Mar 10, 2026Keita BroadwaterLLM Evaluation Language Model Safety Evaluation
Independent Researcher, San Jose, USA
The Reasoning Trap -- Logical Reasoning as a Mechanistic Pathway to Situational Awareness
Mar 10, 2026Subramanyam Sahoo, Aman Chadha, Vinija Jain +1Strategic Reasoning Risks in Language Models LLM Safety Alignment
MARS 4.0 Fellowship, Cambridge AI Safety Hub(CAISH), University of Cambridge · AWS Generative AI Innovation Center, Amazon Web Services, USA · Stanford University +2
ADVERSA: Measuring Multi-Turn Guardrail Degradation and Judge Reliability in Large Language Models
Mar 10, 2026Harry Owiredu-AshleyLanguage Model Safety Evaluation Adversarial Attacks on LLMs
Independent Researcher, New Jersey, United States
AdaCultureSafe: Adaptive Cultural Safety Grounded by Cultural Knowledge in Large Language Models
Mar 9, 2026Hankun Kang, Di Lin, Zhirong Liao +6Language Model Safety Evaluation Cultural Knowledge in Language Models
School of Computer Science, Wuhan University, China · Tsinghua University, China · Jiangxi University of Finance and Economics, China
AutoControl Arena: Synthesizing Executable Test Environments for Frontier AI Risk Evaluation
Mar 8, 2026Changyi Li, Pengfei Lu, Xudong Pan +2Language Model Safety Evaluation AI Agent Safety Benchmarks
Fudan University, Shanghai, China · Shanghai Innovation Institute, Shanghai, China · University of Oxford, Oxford, United Kingdom +2
Taiwan Safety Benchmark and Breeze Guard: Toward Trustworthy AI for Taiwanese Mandarin
Mar 7, 2026Po-Chun Hsu, Meng-Hsi Chen, Tsu Ling Chao +2LLM Safety Language Model Safety Evaluation
MediaTek Research · National Taiwan University
Lying to Win: Assessing LLM Deception through Human-AI Games and Parallel-World Probing
Mar 7, 2026Arash Marioriyad, Ali Nouri, Mohammad Hossein Rohban +1Deception in Language Models Language Model Safety Evaluation
Sharif University of Technology
LieCraft: A Multi-Agent Framework for Evaluating Deceptive Capabilities in Language Models
Mar 6, 2026Matthew Lyle Olson, Neale Ratzlaff, Musashi Hinck +5Deception in Language Models Language Model Safety Evaluation
Oracle · Intel Labs · Oregon State University +2
Reasoning Models Struggle to Control their Chains of Thought
Mar 5, 2026Chen Yueh-Han, Robert McCarthy, Bruce W. Lee +5CoT Monitoring Large Reasoning Models
NYU, MATS · UCL, MATS · UPenn, MATS +2
ThaiSafetyBench: Assessing Language Model Safety in Thai Cultural Contexts
Mar 5, 2026Trapoom Ukarapol, Nut Chukamphaeng, Kunat Pipatanakul +1Language Model Safety Evaluation LLM Safety
SCB DataX · Department of Computer Science and Technology, Tsinghua University · SCBX R&D +1
Alignment Backfire: Language-Dependent Reversal of Safety Interventions Across 16 Languages in LLM Multi-Agent Systems
Mar 5, 2026Hiroki FukuiLLM Safety LLM Alignment
Research Institute of Criminal Psychiatry / Sex Offender Medical Center; Department of Neuropsychiatry, Kyoto University
When Agents Persuade: Rhetoric Generation and Mitigation in LLMs
Mar 4, 2026Julia Jose, Ritik Roongta, Rachel GreenstadtPersuasion in Language Models LLM Agent Safety
Department of Computer Science and Engineering, New York University, New York, NY, USA
The Company You Keep: How LLMs Respond to Dark Triad Traits
Mar 4, 2026Angelica Henestrosa, Zeyi Lu, Pavel Chizhov +1Language Model Safety Evaluation LLM Sycophancy
CAIRO, Technical University of Applied Sciences Würzburg-Schweinfurt
FINEST: Improving LLM Responses to Sensitive Topics Through Fine-Grained Evaluation
Mar 4, 2026Juhyun Oh, Nayeon Lee, Chani Jung +5Language Model Generation Evaluation Language Model Safety Evaluation
School of Computing, KAIST, Daejeon, Republic of Korea · Samsung, Suwon, Republic of Korea
Internal Safety Collapse in Frontier Large Language Models
Mar 4, 2026Yutao Wu, Xiao Liu, Yifeng Gao +7LLM Safety Language Model Safety Evaluation
Deakin University · Institute of Trustworthy Embodied AI, Fudan University · Shanghai Key Laboratory of Multimodal Embodied AI +4
Residual Stream Analysis of Overfitting And Structural Disruptions
Mar 4, 2026Quan Liu, Han Zhou, Wenquan Wu +2Safety-Preserving Fine-Tuning of Language Models Refusal Behavior in Language Models
BUPT · Baidu
Evaluating Large Language Models' Responses to Sexual and Reproductive Health Queries in Nepali
Mar 4, 2026Medha Sharma, Supriya Khadka, Udit Chandra Aryal +15Language Model Safety Evaluation Medical QA
Visible Impact (Visim), Kathmandu, 44600, Nepal · Diyo.AI, Lalitpur, 44600, Nepal · Nepal Applied Mathematics and Informatics Institute for research (NAAMII), Lalitpur, 44600, Nepal +1
Learning When to Act or Refuse: Guarding Agentic Reasoning Models for Safe Multi-Step Tool Use
Mar 3, 2026Aradhye Agarwal, Gurdit Siyan, Yash Pandya +3LLM Agent Safety Tool-Using Language Agents
Microsoft Research
MUSE: A Run-Centric Platform for Multimodal Unified Safety Evaluation of Large Language Models
Mar 3, 2026Zhongxi Wang, Yueqian Lin, Jingyang Zhang +3LLM Safety Benchmarks LLM Safety
1Duke University · 2Virtue AI
Frontier Models Can Take Actions at Low Probabilities
Mar 2, 2026Alex Serrano, Wen Xing, David Lindner +1Language Model Safety Evaluation Strategic Reasoning Risks in Language Models
MATS† · Google DeepMind
RedacBench: Can AI Erase Your Secrets?
Mar 2, 2026Hyunjun Jeon, Kyuyoung Kim, Jinwoo ShinLanguage Model Safety Evaluation Privacy Leakage in Language Models
Korea Advanced Institute of Science and Technology
Policy Compliance of User Requests in Natural Language for AI Systems
Feb 27, 2026Pedro Cisneros-VelardeLLM Safety Benchmarks Language Model Safety Evaluation
VMware Research
LSR: Linguistic Safety Robustness Benchmark for Low-Resource West African Languages
Feb 27, 2026Godwin Abuh FarunaLLM Safety Benchmarks Language Model Safety Evaluation
Fagmart Lab

Mar 15, 2026J/K move · Enter open · S save

State-Dependent Safety Failures in Multi-Turn Language Model Interaction

Pengcheng Li, Jie Zhang, Tianwei Zhang, Han Qiu+4

School of Cyber Science and Technology, University of Science and Technology of China, China · Agency for Science, Technology and Research (A*STAR), Singapore · Nanyang Technological University, Singapore+3

LLM Safety Language Model Safety Evaluation

Open paper AskPDF arXiv

Safety alignment in large language models is typically evaluated under isolated queries, yet real-world use is inherently multi-turn. Although multi-turn jailbreaks are empirically effective, the structure of conversational safety failure remains insufficiently understood. In this work, we study safety failures from a state-space perspective and show that many multi-turn safety failures in current safety-aligned language models arise from contextual state evolution, a regime that is not fully captured by isolated prompt-level analyses alone. We introduce STAR, a state-oriented diagnostic framework that treats dialogue history as a state transition operator and enables controlled analysis of safety behavior along interaction trajectories. Rather than optimizing attack strength, STAR provides a principled probe of how aligned models traverse the safety boundary under autoregressive conditioning. Across multiple frontier language models, we find that systems that appear robust under static evaluation can undergo rapid and reproducible safety collapse under structured multi-turn interaction. Mechanistic analysis reveals monotonic drift away from refusal-related representations and abrupt phase transitions induced by role-conditioned context. Together, these findings motivate viewing language model safety as a dynamic, state-dependent process defined over conversational trajectories.