LLM Safety Benchmarks

LLM: Large Language Model

This field measures how reliably language models recognize and handle risks such as harmful requests, jailbreaks, bias, privacy violations, and unsafe tool use. Benchmarks use curated and expert-annotated scenarios, adversarial red-teaming, multi-turn and agent simulations, and increasingly multilingual, multimodal, and domain-specific tests. Researchers also compare refusal and moderation methods, use repeated sampling and statistical techniques to estimate reliability, and assess both harmful compliance and over-refusal. A central challenge is making results comparable and trustworthy while ensuring tests reflect changing, context-dependent behavior in real deployments.

Latest papers

284 papers44 papers in the last four weeks, up 7% on the four weeks before. 0.3% of all new papers.

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
MedMT-Bench: Can LLMs Memorize and Understand Long Multi-Turn Conversations in Medical Scenarios?
Mar 6, 2026Lin Yang, Yuancheng Yang, Xu Wang +2Long-Context Language Model Evaluation Clinical Language Model Evaluation
ByteDance
Knowing without Acting: The Disentangled Geometry of Safety Mechanisms in Large Language Models
Mar 6, 2026Jinman Wu, Yi Xie, Shen Lin +2Refusal Mechanisms in Language Models LLM Safety Alignment
Xidian University, Xi’an, China · Tsinghua University, Shenzhen, China · Fujian Normal University, Fuzhou, China +1
Survive at All Costs: Exploring LLM's Risky Behaviors under Survival Pressure
Mar 5, 2026Yida Lu, Jianwei Fang, Xuyang Shao +7LLM Safety AI Agent Safety
The Conversational AI (CoAI) group, DCST, Tsinghua University · China Unicom Software Research Institute · University of Electronic Science and Technology of China +1
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
Design Behaviour Codes (DBCs): A Taxonomy-Driven Layered Governance Benchmark for Large Language Models
Mar 5, 2026G. Madan Mohan, Veena Kiran Nambiar, Kiranmayee JanardhanLLM Safety Benchmarks LLM Guardrails
Founder, Yonih Ventures, Bangalore, India | Canada · Professor, Ramaiah University of Applied Sciences, Bangalore, India · Data Scientist, Bangalore, India
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
TrustMH-Bench: A Comprehensive Benchmark for Evaluating the Trustworthiness of Large Language Models in Mental Health
Mar 3, 2026Zixin Xiong, Ziteng Wang, Haotian Fan +2LLM Safety Benchmarks LLM Reliability
Renmin University of China, China · Beijing University of Posts and Telecommunications, China · Hefei University of Technology, China
Benchmark of Benchmarks: Unpacking Influence and Code Repository Quality in LLM Safety Benchmarks
Mar 3, 2026Junjie Chu, Xinyue Shen, Ye Leng +3Benchmark Reproducibility LLM Safety Benchmarks
CISPA Helmholtz Center for Information Security · University of Waterloo · Flexera
ExpGuard: LLM Content Moderation in Specialized Domains
Mar 3, 2026Minseok Choi, Dongjin Kim, Seungbin Yang +5LLM Guardrails Content Moderation
KAIST AI · Financial Tech Lab, KakaoBank Corp
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
SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond
Mar 2, 2026Xiangyang Zhu, Yuan Tian, Qi Jia +14LLM Safety LLM Safety Evaluation
Shanghai AI Lab · ByteDance · ECNU
Quantifying Frontier LLM Capabilities for Container Sandbox Escape
Mar 1, 2026Rahul Marchand, Art O Cathain, Jerome Wynne +8LLM Safety Benchmarks LLM Agent Security
University of Oxford · UK AI Security Institute
JailNewsBench: Multi-Lingual and Regional Benchmark for Fake News Generation under Jailbreak Attacks
Mar 1, 2026Masahiro Kaneko, Ayana Niwa, Timothy BaldwinLLM Safety Benchmarks LLM Jailbreak Attacks
MBZUAI
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
Jailbreak Foundry: From Papers to Runnable Attacks for Reproducible Benchmarking
Feb 27, 2026Zhicheng Fang, Jingjie Zheng, Chenxu Fu +1Jailbreak Attack Evaluation LLM Safety Benchmarks
Shanghai Qi Zhi Institute, Shanghai, China · University of Melbourne, Melbourne, Australia · Tsinghua University, Beijing, China
FlexGuard: Continuous Risk Scoring for Strictness-Adaptive LLM Content Moderation
Feb 27, 2026Zhihao Ding, Jinming Li, Ze Lu +1Content Moderation LLM Guardrails
The Hong Kong Polytechnic University · ByteDance
ClinDet-Bench: Beyond Abstention, Evaluating Judgment Determinability of LLMs in Clinical Decision-Making
Feb 26, 2026Yusuke Watanabe, Yohei Kobashi, Takeshi Kojima +3Clinical Language Model Evaluation LLM Safety Benchmarks
Kyoto University, Department of Biomedical Data Intelligence · Kyoto University, Department of Cardiovascular Medicine · The University of Tokyo
Reverse CAPTCHA: Evaluating LLM Susceptibility to Invisible Unicode Instruction Injection
Feb 26, 2026Marcus GravesPrompt Injection Attacks on LLMs Prompt Injection
Independent Researcher
SPOC: Safety-Aware Planning Under Partial Observability And Physical Constraints
Feb 25, 2026Hyungmin Kim, Hobeom Jeon, Dohyung Kim +2Robot Task Planning Large Language Model-Based Robot Planning
ETRI School, University of Science and Technology, South Korean · Social Robotics Laboratory, Electronics and Telecommunication Research Institute, South Korea
Evaluating Proactive Risk Awareness of Large Language Models
Feb 24, 2026Xuan Luo, Yubin Chen, Zhiyu Hou +4LLM Safety Evaluation LLM Safety Benchmarks
The Harbin Institute of Technology, Shenzhen · The Hong Kong Polytechnic University, Hong Kong · Southern University of Science and Technology, Shenzhen +1
Pressure Reveals Character: Behavioural Alignment Evaluation at Depth
Feb 24, 2026Nora Petrova, John BurdenLLM Alignment LLM Safety Benchmarks
Prolific
TherapyGym: Evaluating and Aligning Clinical Fidelity and Safety in Therapy Chatbots
Feb 23, 2026Fangrui Huang, Souhad Chbeir, Arpandeep Khatua +8Mental Health Conversational Agents Clinical Language Model Evaluation
Department of Computer Science, Stanford University, Stanford, CA, USA · Department of Psychiatry and Behavioral Sciences, Stanford University, Stanford, CA, USA · The University of Hong Kong, Hong Kong +2
Hiding in Plain Text: Detecting Concealed Jailbreaks via Activation Disentanglement
Feb 23, 2026Amirhossein Farzam, Majid Behabahani, Mani Malek +2LLM Security Representation Disentanglement
Duke University · Princeton University · Morgan Stanley +2
LLM Spirals of Delusion: A Benchmarking Audit Study of AI Chatbot Interfaces
Feb 20, 2026Peter Kirgis, Ben Hawriluk, Sherrie Feng +3Language Model Safety Evaluation LLM Safety Benchmarks
Princeton University · Phillips Exeter Academy · Independent
FENCE: A Financial and Multimodal Jailbreak Detection Dataset
Feb 20, 2026Mirae Kim, Seonghun Jeong, Youngjun KwakJailbreak Detection Multimodal Jailbreak Attacks
Kakaobank, South Korea
IndicJR: A Judge-Free Benchmark of Jailbreak Robustness in South Asian Languages
Feb 18, 2026Priyaranjan Pattnayak, Sanchari ChowdhuriAdversarial Robustness of Language Models LLM Safety Benchmarks
Oracle America Inc.

Mar 7, 2026J/K move · Enter open · S save

Taiwan Safety Benchmark and Breeze Guard: Toward Trustworthy AI for Taiwanese Mandarin

Po-Chun Hsu, Meng-Hsi Chen, Tsu Ling Chao, Chia Tien Han+1

MediaTek Research · National Taiwan University

LLM Safety Language Model Safety Evaluation LLM Safety Benchmarks Cultural Knowledge in Language Models Cross-Cultural Language Model Evaluation

Open paper AskPDF arXiv

Global safety models exhibit strong performance across widely used benchmarks, yet their training data rarely captures the cultural and linguistic nuances of Taiwanese Mandarin. This limitation results in systematic blind spots when interpreting region-specific risks such as localized financial scams, culturally embedded hate speech, and misinformation patterns. To address these gaps, we introduce TS-Bench (Taiwan Safety Benchmark), a standardized evaluation suite for assessing safety performance in Taiwanese Mandarin. TS-Bench contains 400 human-curated prompts spanning critical domains including financial fraud, medical misinformation, social discrimination, and political manipulation. In parallel, we present Breeze Guard, an 8B safety model derived from Breeze 2, our previously released general-purpose Taiwanese Mandarin LLM with strong cultural grounding from its original pre-training corpus. Breeze Guard is obtained through supervised fine-tuning on a large-scale, human-verified synthesized dataset targeting Taiwan-specific harms. Our central hypothesis is that effective safety detection requires the cultural grounding already present in the base model; safety fine-tuning alone is insufficient to introduce new socio linguistic knowledge from scratch. Empirically, Breeze Guard significantly outperforms the leading 8B general-purpose safety model, Granite Guardian 3.3, on TS-Bench (+0.17 overall F1), with particularly large gains in high-context categories such as scam (+0.66 F1) and financial malpractice (+0.43 F1). While the model shows slightly lower performance on English-centric benchmarks (ToxicChat, AegisSafetyTest), this tradeoff is expected for a regionally specialized safety model optimized for Taiwanese Mandarin. Together, Breeze Guard and TS-Bench establish a new foundation for trustworthy AI deployment in Taiwan.