{"total":53,"rows":[{"id":"2310.12773","title":"Safe RLHF: Safe Reinforcement Learning from Human Feedback","created":"2023-10-19","cited_by_count":656,"area":"alignment"},{"id":"2310.02446","title":"Low-Resource Languages Jailbreak GPT-4","created":"2023-10-03","cited_by_count":309,"area":"safety"},{"id":"2406.15513","title":"PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference","created":"2024-06-20","cited_by_count":261,"area":"alignment"},{"id":"2502.17420","title":"The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence","created":"2025-02-24","cited_by_count":115,"area":"alignment"},{"id":"2406.18682","title":"The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm","created":"2024-06-26","cited_by_count":70,"area":"safety"},{"id":"2407.01599","title":"JailbreakZoo: Survey, Landscapes, and Horizons in Jailbreaking Large Language and Vision-Language Models","created":"2024-06-26","cited_by_count":70,"area":"mllm"},{"id":"2407.09121","title":"Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training","created":"2024-07-12","cited_by_count":69,"area":null},{"id":"2504.04377","title":"PolyGuard: A Multilingual Safety Moderation Tool for 17 Languages","created":"2025-04-06","cited_by_count":59,"area":null},{"id":"2404.01349","title":"Fairness in Large Language Models: A Taxonomic Survey","created":"2024-03-31","cited_by_count":58,"area":null},{"id":"2506.11094","title":"The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMs","created":"2025-06-06","cited_by_count":26,"area":null},{"id":"2401.10647","title":"Sowing the Wind, Reaping the Whirlwind: The Impact of Editing Language Models","created":"2024-01-19","cited_by_count":20,"area":"safety"},{"id":"2405.09373","title":"PolygloToxicityPrompts: Multilingual Evaluation of Neural Toxic Degeneration in Large Language Models","created":"2024-05-15","cited_by_count":20,"area":null},{"id":"2402.08323","title":"Mapping the Ethics of Generative AI: A Comprehensive Scoping Review","created":"2024-02-13","cited_by_count":19,"area":null},{"id":"2502.05163","title":"Enhancing LLM Safety Through a Theoretical Minimax Game Lens","created":"2025-02-07","cited_by_count":19,"area":"safety"},{"id":"2411.11072","title":"Multilingual Large Language Models: A Systematic Survey","created":"2024-11-17","cited_by_count":18,"area":null},{"id":"2410.10801","title":"Mix Data or Merge Models? Optimizing for Diverse Multi-Task Learning","created":"2024-10-14","cited_by_count":17,"area":null},{"id":"2401.00763","title":"New Job, New Gender? Measuring the Social Bias in Image Generation Models","created":"2024-01-01","cited_by_count":16,"area":null},{"id":"2406.10311","title":"CHiSafetyBench: A Chinese Hierarchical Safety Benchmark for Large Language Models","created":"2024-06-14","cited_by_count":15,"area":null},{"id":"2606.28733","title":"Agentic Abstention: Do Agents Know When to Stop Instead of Act?","created":"2026-06-27","cited_by_count":15,"area":"agents"},{"id":"2602.22983","title":"Obscure but Effective: Classical Chinese Jailbreak Prompt Optimization via Bio-Inspired Search","created":"2026-02-26","cited_by_count":13,"area":"safety"},{"id":"2412.16974","title":"Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs","created":"2024-12-22","cited_by_count":11,"area":"alignment"},{"id":"2509.07604","title":"K2-Think: A Parameter-Efficient Reasoning System","created":"2025-09-09","cited_by_count":11,"area":"lr"},{"id":"2504.15241","title":"MrGuard: A Multilingual Reasoning Guardrail for Universal LLM Safety","created":"2025-04-21","cited_by_count":9,"area":"lr"},{"id":"2602.16660","title":"Align Once, Benefit Multilingually: Enforcing Multilingual Consistency for LLM Safety Alignment","created":"2026-02-18","cited_by_count":9,"area":"alignment"},{"id":"2410.12999","title":"POROver: Improving Safety and Reducing Overrefusal in Large Language Models with Overgeneration and Preference Optimization","created":"2024-10-16","cited_by_count":8,"area":"alignment"},{"id":"2412.15035","title":"LLMs Lost in Translation: M-ALERT uncovers Cross-Linguistic Safety Inconsistencies","created":"2024-12-19","cited_by_count":7,"area":null},{"id":"2408.14398","title":"On the Limitations of Language Targeted Pruning: Investigating the Calibration Language Impact in Multilingual LLM Pruning","created":"2024-08-26","cited_by_count":6,"area":null},{"id":"2404.02532","title":"Learn to Disguise: Avoid Refusal Responses in LLM's Defense via a Multi-agent Attacker-Disguiser Game","created":"2024-04-03","cited_by_count":5,"area":"safety"},{"id":"2502.18935","title":"JailBench: A Comprehensive Chinese Security Assessment Benchmark for Large Language Models","created":"2025-02-26","cited_by_count":5,"area":"safety"},{"id":"2506.00469","title":"Massively Multilingual Adaptation of Large Language Models Using Bilingual Translation Data","created":"2025-05-31","cited_by_count":4,"area":null},{"id":"2602.11157","title":"Response-Based Knowledge Distillation for Multilingual Jailbreak Prevention Unwittingly Compromises Safety","created":"2025-12-08","cited_by_count":4,"area":"alignment"},{"id":"2505.12287","title":"The Tower of Babel Revisited: Multilingual Jailbreak Prompts on Closed-Source Large Language Models","created":"2025-05-18","cited_by_count":3,"area":"safety"},{"id":"2602.04581","title":"Trust The Typical","created":"2026-02-04","cited_by_count":3,"area":"safety"},{"id":"2602.20170","title":"CAGE: A Framework for Culturally Adaptive Red-Teaming Benchmark Generation","created":"2026-02-09","cited_by_count":3,"area":"safety"},{"id":"2605.02971","title":"Multilingual Safety Alignment via Self-Distillation","created":"2026-05-03","cited_by_count":3,"area":"alignment"},{"id":"2409.13708","title":"Towards Safe Multilingual Frontier AI","created":"2024-09-06","cited_by_count":2,"area":"safety"},{"id":"2410.03568","title":"Towards Linguistically-Aware and Language-Independent Tokenization for Large Language Models (LLMs)","created":"2024-10-04","cited_by_count":2,"area":null},{"id":"2507.07146","title":"Attention-Aware GNN-based Input Defense against Multi-Turn LLM Jailbreak","created":"2025-07-09","cited_by_count":2,"area":"safety"},{"id":"2510.03969","title":"How Catastrophic is Your LLM? Certifying Risk in Conversation","created":"2025-10-04","cited_by_count":2,"area":null},{"id":"2602.22562","title":"Layer-Targeted Multilingual Knowledge Erasure in Large Language Models","created":"2026-02-26","cited_by_count":2,"area":"safety"},{"id":"2412.13705","title":"Mitigating Adversarial Attacks in LLMs through Defensive Suffix Generation","created":"2024-12-18","cited_by_count":1,"area":null},{"id":"2606.25476","title":"A Red Teaming Framework for Large Language Models: A Case Study on Faithfulness Evaluation","created":"2026-06-24","cited_by_count":1,"area":"safety"},{"id":"2506.17878","title":"Towards Robust Fact-Checking: A Multi-Agent System with Advanced Evidence Retrieval","created":"2025-06-22","cited_by_count":0,"area":"agents"},{"id":"2603.04992","title":"ThaiSafetyBench: Assessing Language Model Safety in Thai Cultural Contexts","created":"2026-03-05","cited_by_count":0,"area":"safety"},{"id":"2605.17173","title":"Why Do Safety Guardrails Degrade Across Languages?","created":"2026-05-16","cited_by_count":0,"area":"safety"},{"id":"2605.29659","title":"Opir: Efficient Multi-Task Safety Classification for Toxicity, Jailbreaks, Hate Speech, and Harmful Content","created":"2026-05-28","cited_by_count":0,"area":"safety"},{"id":"2606.09178","title":"Culturally-Adapted Red-Teaming Across East and Southeast Asian Contexts: A Methodological and Comparative Analysis","created":"2026-06-08","cited_by_count":0,"area":"safety"},{"id":"2607.17270","title":"Safety That Does Not Transfer: Cross-Lingual Clinical Correctness Drift in Deployable Medical Language Models","created":"2026-07-19","cited_by_count":0,"area":null},{"id":"2608.08383","title":"Safety Cost of Steering Vectors Is Separable and Reducible","created":"2026-08-09","cited_by_count":0,"area":"mechinterp"},{"id":"2608.17744","title":"Thinking in a Low-Resource Language: What SFT Builds, What RL Fixes, What Accuracy Cannot See","created":"2026-08-18","cited_by_count":0,"area":"moe"},{"id":"2608.27548","title":"Nemotron 3.5 Content Safety Moderator: A Compact Multimodal, Multilingual, and Reasoning Enabled Content Safety Moderator","created":"2026-08-27","cited_by_count":0,"area":"safety"},{"id":"2609.01046","title":"HiveTraceGuard-Pro: A Compact Generative Guardrail for Prompt Injection, Jailbreaks, and Adversarial Obfuscation","created":"2026-09-01","cited_by_count":0,"area":"safety"},{"id":"2610.06563","title":"HERA: Harness-Environment Co-Evolution for Reliable Agentic Abstention","created":"2026-10-05","cited_by_count":0,"area":"agents"}],"next_cursor":null}