{"total":76,"rows":[{"id":"2406.18495","title":"WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs","created":"2024-06-26","cited_by_count":496,"area":"safety"},{"id":"2404.02151","title":"Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks","created":"2024-04-02","cited_by_count":486,"area":"safety"},{"id":"2406.14598","title":"SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal","created":"2024-06-20","cited_by_count":240,"area":"alignment"},{"id":"2405.17247","title":"An Introduction to Vision-Language Modeling","created":"2024-05-27","cited_by_count":178,"area":"mllm"},{"id":"2407.15549","title":"Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs","created":"2024-07-22","cited_by_count":173,"area":"safety"},{"id":"2510.14276","title":"Qwen3Guard Technical Report","created":"2025-10-16","cited_by_count":155,"area":"safety"},{"id":"2404.05993","title":"AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts","created":"2024-04-09","cited_by_count":136,"area":null},{"id":"2505.23836","title":"Large Language Models Often Know When They Are Being Evaluated","created":"2025-05-28","cited_by_count":128,"area":null},{"id":"2311.16101","title":"How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs","created":"2023-11-27","cited_by_count":108,"area":"lr"},{"id":"2501.18492","title":"GuardReasoner: Towards Reasoning-based LLM Safeguards","created":"2025-01-30","cited_by_count":100,"area":"lr"},{"id":"2404.05399","title":"SafetyPrompts: a Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safety","created":"2024-04-08","cited_by_count":77,"area":"safety"},{"id":"2504.01903","title":"STAR-1: Safer Alignment of Reasoning LLMs with 1K Data","created":"2025-04-02","cited_by_count":68,"area":"lr"},{"id":"2404.12241","title":"Introducing v0.5 of the AI Safety Benchmark from MLCommons","created":"2024-04-18","cited_by_count":62,"area":null},{"id":"2410.03415","title":"Surgical, Cheap, and Flexible: Mitigating False Refusal in Language Models via Single Vector Ablation","created":"2024-10-04","cited_by_count":48,"area":null},{"id":"2505.11049","title":"GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning","created":"2025-05-16","cited_by_count":42,"area":"lr"},{"id":"2410.08968","title":"Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements","created":"2024-10-11","cited_by_count":36,"area":"alignment"},{"id":"2409.14586","title":"Backtracking Improves Generation Safety","created":"2024-09-22","cited_by_count":32,"area":"alignment"},{"id":"2509.03871","title":"A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models","created":"2025-09-04","cited_by_count":25,"area":"lr"},{"id":"2501.18438","title":"o3-mini vs DeepSeek-R1: Which One is Safer?","created":"2025-01-30","cited_by_count":24,"area":"lr"},{"id":"2410.10414","title":"On Calibration of LLM-based Guard Models for Reliable Content Moderation","created":"2024-10-14","cited_by_count":23,"area":"safety"},{"id":"2501.14940","title":"CASE-Bench: Context-Aware SafEty Benchmark for Large Language Models","created":"2025-01-24","cited_by_count":20,"area":"alignment"},{"id":"2601.15588","title":"YuFeng-XGuard: A Reasoning-Centric, Interpretable, and Flexible Guardrail Model for Large Language Models","created":"2026-01-22","cited_by_count":19,"area":"lr"},{"id":"2502.15799","title":"Investigating the Impact of Quantization Methods on the Safety and Reliability of Large Language Models","created":"2025-02-18","cited_by_count":18,"area":"lr"},{"id":"2506.17368","title":"SAFEx: Analyzing Vulnerabilities of MoE-Based LLMs via Stable Safety-critical Expert Identification","created":"2025-06-20","cited_by_count":18,"area":"alignment"},{"id":"2505.20087","title":"Safety Through Reasoning: An Empirical Study of Reasoning Guardrail Models","created":"2025-05-26","cited_by_count":16,"area":"lr"},{"id":"2404.03820","title":"CantTalkAboutThis: Aligning Language Models to Stay on Topic in Dialogues","created":"2024-04-04","cited_by_count":15,"area":"lr"},{"id":"2501.17749","title":"Early External Safety Testing of OpenAI's o3-mini: Insights from the Pre-Deployment Evaluation","created":"2025-01-29","cited_by_count":13,"area":"lr"},{"id":"2406.16746","title":"The Responsible Foundation Model Development Cheatsheet: A Review of Tools & Resources","created":"2024-06-24","cited_by_count":11,"area":null},{"id":"2509.07604","title":"K2-Think: A Parameter-Efficient Reasoning System","created":"2025-09-09","cited_by_count":11,"area":"lr"},{"id":"2510.01270","title":"Think Twice, Generate Once: Safeguarding by Progressive Self-Reflection","created":"2025-09-29","cited_by_count":11,"area":"lr"},{"id":"2407.11733","title":"How Are LLMs Mitigating Stereotyping Harms? Learning from Search Engine Studies","created":"2024-07-16","cited_by_count":10,"area":null},{"id":"2410.16665","title":"SafetyAnalyst: Interpretable, Transparent, and Steerable Safety Moderation for AI Behavior","created":"2024-10-22","cited_by_count":10,"area":null},{"id":"2602.08621","title":"Sparse Models, Sparse Safety: Unsafe Routes in Mixture-of-Experts LLMs","created":"2026-02-09","cited_by_count":9,"area":"moe"},{"id":"2501.17132","title":"ASTRAL: Automated Safety Testing of Large Language Models","created":"2025-01-28","cited_by_count":7,"area":null},{"id":"2312.13096","title":"In Generative AI we Trust: Can Chatbots Effectively Verify Political Information?","created":"2023-12-20","cited_by_count":6,"area":null},{"id":"2408.16163","title":"FRACTURED-SORRY-Bench: Framework for Revealing Attacks in Conversational Turns Undermining Refusal Efficacy and Defenses over SORRY-Bench (Automated Multi-shot Jailbreaks)","created":"2024-08-28","cited_by_count":6,"area":"safety"},{"id":"2606.22873","title":"SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning","created":"2026-06-22","cited_by_count":6,"area":"lr"},{"id":"2502.13603","title":"Efficient Safety Retrofitting Against Jailbreaking for LLMs","created":"2025-02-19","cited_by_count":4,"area":"alignment"},{"id":"2502.16174","title":"Efficient LLM Moderation with Multi-Layer Latent Prototypes","created":"2025-02-22","cited_by_count":4,"area":"safety"},{"id":"2512.23573","title":"ProGuard: Towards Proactive Multimodal Safeguard","created":"2025-12-29","cited_by_count":4,"area":null},{"id":"2601.17003","title":"Beyond Simulations: What 20,000 Real Conversations Reveal About Mental Health AI Safety","created":"2026-01-14","cited_by_count":4,"area":null},{"id":"2603.02219","title":"NExT-Guard: Training-Free Streaming Safeguard without Token-Level Labels","created":"2026-02-10","cited_by_count":4,"area":"mechinterp"},{"id":"2605.06605","title":"How Many Iterations to Jailbreak? Dynamic Budget Allocation for Multi-Turn LLM Evaluation","created":"2026-05-07","cited_by_count":4,"area":"safety"},{"id":"2605.07982","title":"GLiGuard: Schema-Conditioned Classification for LLM Safeguard","created":"2026-05-08","cited_by_count":4,"area":"safety"},{"id":"2504.06549","title":"Societal Impacts Research Requires Benchmarks for Creative Composition Tasks","created":"2025-04-09","cited_by_count":3,"area":null},{"id":"2506.13593","title":"Calibrated Predictive Lower Bounds on Time-to-Unsafe-Sampling in LLMs","created":"2025-06-16","cited_by_count":3,"area":null},{"id":"2604.03962","title":"Predict, Don't React: Value-Based Safety Forecasting for LLM Streaming","created":"2026-04-05","cited_by_count":3,"area":"safety"},{"id":"2503.08404","title":"Fact-checking with Generative AI: A Systematic Cross-Topic Examination of LLMs Capacity to Detect Veracity of Political Information","created":"2025-03-11","cited_by_count":2,"area":"safety"},{"id":"2510.08120","title":"Interpreting LLM-as-a-Judge Policies via Verifiable Global Explanations","created":"2025-10-09","cited_by_count":2,"area":null},{"id":"2512.05339","title":"Taxonomy-Adaptive Moderation Model with Robust Guardrails for Large Language Models","created":"2025-12-05","cited_by_count":2,"area":"safety"},{"id":"2512.20293","title":"AprielGuard","created":"2025-12-23","cited_by_count":2,"area":"agents"},{"id":"2604.06233","title":"Blind Refusal: Language Models Refuse to Help Users Evade Unjust, Absurd, and Illegitimate Rules","created":"2026-04-03","cited_by_count":2,"area":null},{"id":"2410.18114","title":"Bridging Today and the Future of Humanity: AI Safety in 2024 and Beyond","created":"2024-10-09","cited_by_count":1,"area":null},{"id":"2604.07655","title":"Guardian-as-an-Advisor: Advancing Next-Generation Guardian Models for Trustworthy LLMs","created":"2026-04-08","cited_by_count":1,"area":null},{"id":"2605.05678","title":"Chain of Risk: Safety Failures in Large Reasoning Models and Mitigation via Adaptive Multi-Principle Steering","created":"2026-05-07","cited_by_count":1,"area":"lr"},{"id":"2606.19168","title":"Beyond Safe Data: Pretraining-Stage Alignment with Regular Safety Reflection","created":"2026-06-17","cited_by_count":1,"area":"alignment"},{"id":"2606.20668","title":"BELLS-O: Evaluating the Operational Trade-offs of LLM Supervision Systems","created":"2026-06-12","cited_by_count":1,"area":"safety"},{"id":"2607.21401","title":"When Are Reasoning-Based Guardrails Not Efficient? ResponseGuard: A Fast Vision-Language Guard for Real-Time Moderation","created":"2026-07-23","cited_by_count":1,"area":"lr"},{"id":"2607.25857","title":"Shieldstral","created":"2026-07-28","cited_by_count":1,"area":null},{"id":"2603.07286","title":"Taiwan Safety Benchmark and Breeze Guard: Toward Trustworthy AI for Taiwanese Mandarin","created":"2026-03-07","cited_by_count":0,"area":null},{"id":"2604.00324","title":"The Persistent Vulnerability of Aligned AI Systems","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2605.10639","title":"Navigating the Sea of LLM Evaluation: Investigating Bias in Toxicity Benchmarks","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.24414","title":"JT-SAFE-V2: Safety-by-Design Foundation Model with World-Context Data","created":"2026-05-23","cited_by_count":0,"area":null},{"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":"2606.20626","title":"Efficient Safety Benchmarking via Item Response Theory","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2607.22545","title":"Semalith v1.4: A Calibrated 184M Safety Classifier Achieving State-of-the-Art Prompt-Injection Detection at 44x Fewer Parameters than Llama-Guard-3-8B","created":"2026-05-06","cited_by_count":0,"area":"agents"},{"id":"2608.03838","title":"LatentGuard: Efficient and Inspectable Latent Reasoning for LLM Safeguards","created":"2026-08-04","cited_by_count":0,"area":"lr"},{"id":"2608.20554","title":"aiXamine: Unified Black-Box Evaluation of Cross-Dimensional Trade-offs in LLM Safety, Security, and Privacy","created":"2026-08-20","cited_by_count":0,"area":"alignment"},{"id":"2608.21570","title":"A Reproducible, License-Aware Distillation Recipe for CPUDeployable Safety Classification","created":"2026-08-21","cited_by_count":0,"area":null},{"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":"2609.09793","title":"How Fragile Is Safety Alignment at Frontier Scale? A Single-Direction Attack on a 320B MoE","created":"2026-09-09","cited_by_count":0,"area":"alignment"},{"id":"2609.13534","title":"Harmfulness Propagation Dynamics: Layer-wise Trajectories of Adversarial Intent in Large Language Models","created":"2026-09-11","cited_by_count":0,"area":"safety"},{"id":"2609.25808","title":"Auditing Proxy-Based Validation Across Text Spans","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.36515","title":"Large-scale factor analysis shows machine intelligence is only partially interpretable","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38357","title":"Evaluating Language Model Safety Across Long Adversarial Conversations","created":"2026-09-29","cited_by_count":0,"area":"safety"},{"id":"2610.12409","title":"Searching for \"Harmful Refusal\": A Psychometric Audit of an AI Safety Benchmark","created":"2026-10-08","cited_by_count":0,"area":null}],"next_cursor":null}