{"total":132,"rows":[{"id":"2510.14276","title":"Qwen3Guard Technical Report","created":"2025-10-16","cited_by_count":155,"area":"safety"},{"id":"2508.14444","title":"NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model","created":"2025-08-20","cited_by_count":108,"area":"lr"},{"id":"2512.20848","title":"Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning","created":"2025-12-23","cited_by_count":104,"area":"lr"},{"id":"2501.18492","title":"GuardReasoner: Towards Reasoning-based LLM Safeguards","created":"2025-01-30","cited_by_count":100,"area":"lr"},{"id":"2504.03624","title":"Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models","created":"2025-04-04","cited_by_count":100,"area":"lr"},{"id":"2502.05206","title":"Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety","created":"2025-02-02","cited_by_count":67,"area":"mllm"},{"id":"2504.17704","title":"Safety in Large Reasoning Models: A Survey","created":"2025-04-24","cited_by_count":64,"area":"lr"},{"id":"2504.04377","title":"PolyGuard: A Multilingual Safety Moderation Tool for 17 Languages","created":"2025-04-06","cited_by_count":59,"area":null},{"id":"2601.21557","title":"Meta Context Engineering via Agentic Skill Evolution","created":"2026-01-29","cited_by_count":49,"area":"agents"},{"id":"2505.11049","title":"GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning","created":"2025-05-16","cited_by_count":42,"area":"lr"},{"id":"2508.18076","title":"Neither Valid nor Reliable? Investigating the Use of LLMs as Judges","created":"2025-08-25","cited_by_count":39,"area":null},{"id":"2508.01710","title":"CultureGuard: Towards Culturally-Aware Dataset and Guard Model for Multilingual Safety Applications","created":"2025-08-03","cited_by_count":27,"area":"agents"},{"id":"2507.00971","title":"Reasoning as an Adaptive Defense for Safety","created":"2025-07-01","cited_by_count":23,"area":"lr"},{"id":"2506.10597","title":"SoK: Evaluating Jailbreak Guardrails for Large Language Models","created":"2025-06-12","cited_by_count":21,"area":"alignment"},{"id":"2509.02563","title":"DynaGuard: A Dynamic Guardian Model With User-Defined Policies","created":"2025-09-02","cited_by_count":19,"area":"safety"},{"id":"2509.03888","title":"False Sense of Security: Why Probing-based Malicious Input Detection Fails to Generalize","created":"2025-09-04","cited_by_count":19,"area":null},{"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":"2512.12069","title":"Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoring","created":"2025-12-12","cited_by_count":11,"area":"lr"},{"id":"2604.18519","title":"LLM Safety From Within: Detecting Harmful Content with Internal Representations","created":"2026-04-20","cited_by_count":11,"area":"safety"},{"id":"2504.15241","title":"MrGuard: A Multilingual Reasoning Guardrail for Universal LLM Safety","created":"2025-04-21","cited_by_count":9,"area":"lr"},{"id":"2505.17244","title":"ReasoningShield: Safety Detection over Reasoning Traces of Large Reasoning Models","created":"2025-05-22","cited_by_count":9,"area":"lr"},{"id":"2510.09694","title":"Kelp: A Streaming Safeguard for Large Models via Latent Dynamics-Guided Risk Detection","created":"2025-10-09","cited_by_count":9,"area":"safety"},{"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":"2510.18214","title":"VLSU: Mapping the Limits of Joint Multimodal Understanding for AI Safety","created":"2025-10-21","cited_by_count":8,"area":null},{"id":"2601.07226","title":"Lost in the Noise: How Reasoning Models Fail with Contextual Distractors","created":"2026-01-12","cited_by_count":8,"area":"lr"},{"id":"2505.14035","title":"ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs","created":"2025-05-20","cited_by_count":7,"area":"lr"},{"id":"2505.23856","title":"OMNIGUARD: An Efficient Approach for AI Safety Moderation Across Languages and Modalities","created":"2025-05-29","cited_by_count":7,"area":"safety"},{"id":"2506.11083","title":"RedDebate: Safer Responses Through Multi-Agent Red Teaming Debates","created":"2025-06-04","cited_by_count":7,"area":"agents"},{"id":"2507.15339","title":"LionGuard 2: Building Lightweight, Data-Efficient & Localised Multilingual Content Moderators","created":"2025-07-21","cited_by_count":7,"area":null},{"id":"2508.14904","title":"Efficient Switchable Safety Control in LLMs via Magic-Token-Guided Co-Training","created":"2025-08-12","cited_by_count":7,"area":"alignment"},{"id":"2602.23636","title":"FlexGuard: Continuous Risk Scoring for Strictness-Adaptive LLM Content Moderation","created":"2026-02-27","cited_by_count":7,"area":null},{"id":"2506.00166","title":"Disentangled Safety Adapters Enable Efficient Guardrails and Flexible Inference-Time Alignment","created":"2025-05-30","cited_by_count":6,"area":"alignment"},{"id":"2607.19829","title":"DARWIN: Evolving Jailbreak Adversary and Guardrail for LLM Safety Evaluation and Protection","created":"2026-07-22","cited_by_count":6,"area":"safety"},{"id":"2510.06915","title":"LongRM: Revealing and Unlocking the Context Boundary of Reward Modeling","created":"2025-10-08","cited_by_count":5,"area":"alignment"},{"id":"2601.12696","title":"UbuntuGuard: A Culturally-Grounded Policy Benchmark for Equitable AI Safety in African Languages","created":"2026-01-19","cited_by_count":5,"area":null},{"id":"2604.02045","title":"BidirLM: From Text to Omnimodal Bidirectional Encoders by Adapting and Composing Causal LLMs","created":"2026-04-02","cited_by_count":5,"area":null},{"id":"2605.17329","title":"LPG: Balancing Efficiency and Policy Reasoning in Latent Policy Guardrails","created":"2026-05-17","cited_by_count":5,"area":"lr"},{"id":"2605.17467","title":"VerifyMAS: Hypothesis Verification for Failure Attribution in LLM Multi-Agent Systems","created":"2026-05-17","cited_by_count":5,"area":"agents"},{"id":"2605.18549","title":"Monitoring the Internal Monologue: Probe Trajectories Reveal Reasoning Dynamics","created":"2026-05-18","cited_by_count":5,"area":"lr"},{"id":"2512.23573","title":"ProGuard: Towards Proactive Multimodal Safeguard","created":"2025-12-29","cited_by_count":4,"area":null},{"id":"2601.22313","title":"Hair-Trigger Alignment: Black-Box Evaluation Cannot Guarantee Post-Update Alignment","created":"2026-01-29","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":"2605.07982","title":"GLiGuard: Schema-Conditioned Classification for LLM Safeguard","created":"2026-05-08","cited_by_count":4,"area":"safety"},{"id":"2511.12497","title":"SGuard-v1: Safety Guardrail for Large Language Models","created":"2025-11-16","cited_by_count":3,"area":"safety"},{"id":"2602.08813","title":"Robust Policy Optimization to Prevent Catastrophic Forgetting","created":"2026-02-09","cited_by_count":3,"area":"alignment"},{"id":"2602.13547","title":"AISA: Awakening Intrinsic Safety Awareness in Large Language Models against Jailbreak Attacks","created":"2026-02-14","cited_by_count":3,"area":"safety"},{"id":"2603.01185","title":"Token-level Data Selection for Safe LLM Fine-tuning","created":"2026-03-01","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":"2604.08867","title":"AudioGuard: Toward Comprehensive Audio Safety Protection Across Diverse Threat Models","created":"2026-04-10","cited_by_count":3,"area":"safety"},{"id":"2606.05743","title":"Membrane: A Self-Evolving Contrastive Safety Memory for LLM Agent Defense","created":"2026-06-04","cited_by_count":3,"area":"agents"},{"id":"2504.09712","title":"The Structural Safety Generalization Problem","created":"2025-04-13","cited_by_count":2,"area":"safety"},{"id":"2505.19766","title":"PAM: Training Policy-Aligned Moderation Filters at Scale","created":"2025-05-26","cited_by_count":2,"area":"safety"},{"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":"2509.02372","title":"Scam2Prompt: A Scalable Framework for Auditing Malicious Scam Endpoints in Production LLMs","created":"2025-09-02","cited_by_count":2,"area":null},{"id":"2509.16861","title":"AdaptiveGuard: Towards Adaptive Runtime Safety for LLM-Powered Software","created":"2025-09-21","cited_by_count":2,"area":"safety"},{"id":"2509.22250","title":"Safety Compliance: Rethinking LLM Safety Reasoning through the Lens of Compliance","created":"2025-09-26","cited_by_count":2,"area":"lr"},{"id":"2510.03485","title":"Learning Efficient Guardrails for Compliance","created":"2025-10-03","cited_by_count":2,"area":"agents"},{"id":"2512.02711","title":"CREST: Universal Safety Guardrails Through Cluster-Guided Cross-Lingual Transfer","created":"2025-12-02","cited_by_count":2,"area":"safety"},{"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":"2602.03328","title":"GuardReasoner-Omni: A Reasoning-based Multi-modal Guardrail for Text, Image, Video, and Audio","created":"2026-02-03","cited_by_count":2,"area":"safety"},{"id":"2603.02588","title":"ExpGuard: LLM Content Moderation in Specialized Domains","created":"2026-03-03","cited_by_count":2,"area":"safety"},{"id":"2603.10243","title":"GR-SAP: Generative Replay for Safety Alignment Preservation during Fine-Tuning","created":"2026-03-10","cited_by_count":2,"area":"alignment"},{"id":"2605.05277","title":"GLiNER Guard: Unified Encoder Family for Production LLM Safety and Privacy","created":"2026-05-06","cited_by_count":2,"area":"safety"},{"id":"2605.29427","title":"FinGuard: Detecting Financial Regulatory Non-Compliance in LLM Interactions","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2606.02041","title":"SentGuard: Sentence-Level Streaming Guardrails for Large Language Models","created":"2026-06-01","cited_by_count":2,"area":"lr"},{"id":"2608.08029","title":"Do All LLMs Know When They're Being Harmful? A Reproducibility Study of Latent-Space Safety Probes Across Model Families","created":"2026-08-08","cited_by_count":2,"area":"safety"},{"id":"2602.02509","title":"CodeGuard: Improving LLM Guardrails in CS Education","created":"2026-01-22","cited_by_count":1,"area":"safety"},{"id":"2602.15853","title":"A Lightweight Explainable Guardrail for Prompt Safety","created":"2026-01-24","cited_by_count":1,"area":"safety"},{"id":"2603.13325","title":"Auditing Cascading Risks in Multi-Agent Systems via Semantic-Geometric Co-evolution","created":"2026-03-04","cited_by_count":1,"area":"agents"},{"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":"2604.16542","title":"TWGuard: A Case Study of LLM Safety Guardrails for Localized Linguistic Contexts","created":"2026-04-17","cited_by_count":1,"area":"safety"},{"id":"2605.30693","title":"Triaging Threats to Specialized Guardrails","created":"2026-05-29","cited_by_count":1,"area":"safety"},{"id":"2606.02113","title":"A Primer in Post-Training Reasoning Data: What We Know About How It Works","created":"2026-06-01","cited_by_count":1,"area":"lr"},{"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":"2606.28153","title":"Robust Harmful Features Under Jailbreak Attacks: Mechanistic Evidence from Attention Head Specialization in Large Language Models","created":"2026-06-26","cited_by_count":1,"area":"alignment"},{"id":"2606.29243","title":"KrishokChat: A Provenance-Traceable Multi-Task Bengali Agricultural Benchmark with Safety-Critical Chemical Advisory","created":"2026-06-28","cited_by_count":1,"area":null},{"id":"2606.31435","title":"CDR-Bench: Evaluating Faithful Execution of Compositional, Order-Sensitive Data Refinement Recipes","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2607.02121","title":"Behind the Refusal: Determining Guardrail Activation via Behavioral Monitoring","created":"2026-07-02","cited_by_count":1,"area":"agents"},{"id":"2607.19913","title":"JANUS: Foreseeing Latent Risk for Long-Horizon Agent Safety","created":"2026-07-22","cited_by_count":1,"area":null},{"id":"2607.25857","title":"Shieldstral","created":"2026-07-28","cited_by_count":1,"area":null},{"id":"2608.03201","title":"When Refusal Looks Safe: The Refusal-Cue Shortcut in Safety Guard Models","created":"2026-08-04","cited_by_count":1,"area":"safety"},{"id":"2608.11146","title":"The Illusion of Cross-Lingual Safety in Low-Resource Languages","created":"2026-08-11","cited_by_count":1,"area":"safety"},{"id":"2609.19472","title":"Safety Beyond the Interface: Detecting Harm via Latent States in Large Language Models","created":"2026-09-16","cited_by_count":1,"area":"safety"},{"id":"2503.07550","title":"KSOD: Knowledge Supplement for LLMs On Demand","created":"2025-03-10","cited_by_count":0,"area":null},{"id":"2505.17636","title":"Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2508.02312","title":"Data Security in Large Language Models: Risks, Defense, and Directions","created":"2025-08-04","cited_by_count":0,"area":"safety"},{"id":"2509.23381","title":"Guard Vector: Beyond English LLM Guardrails with Task-Vector Composition and Streaming-Aware Prefix SFT","created":"2025-09-27","cited_by_count":0,"area":"safety"},{"id":"2510.12083","title":"An AI-Based Behavioral Health Safety Filter and Dataset for Identifying Mental Health Crises in Text-Based Conversations","created":"2025-10-14","cited_by_count":0,"area":null},{"id":"2511.05018","title":"Pluralistic Behavior Suite: Stress-Testing Multi-Turn Adherence to Custom Behavioral Policies","created":"2025-11-07","cited_by_count":0,"area":null},{"id":"2512.05501","title":"SEA-SafeguardBench: Evaluating AI Safety in SEA Languages and Cultures","created":"2025-12-05","cited_by_count":0,"area":"safety"},{"id":"2512.21107","title":"Semi-Supervised Learning for Large Language Models Safety and Content Moderation","created":"2025-12-24","cited_by_count":0,"area":null},{"id":"2601.04389","title":"Safety Is Not Universal: The Selective Safety Trap in LLM Alignment","created":"2026-01-07","cited_by_count":0,"area":"alignment"},{"id":"2602.02536","title":"From Sparse Decisions to Dense Reasoning: A Multi-attribute Trajectory Paradigm for Multimodal Moderation","created":"2026-01-28","cited_by_count":0,"area":"safety"},{"id":"2603.02675","title":"From Shallow to Deep: Pinning Semantic Intent via Causal GRPO","created":"2026-03-03","cited_by_count":0,"area":"lr"},{"id":"2603.27065","title":"Story2Proposal: A Scaffold for Structured Scientific Paper Writing","created":"2026-03-28","cited_by_count":0,"area":null},{"id":"2604.22154","title":"Reliable Self-Harm Risk Screening via Adaptive Multi-Agent LLM Systems","created":"2026-04-24","cited_by_count":0,"area":"agents"},{"id":"2604.23067","title":"Training a General Purpose Automated Red Teaming Model","created":"2026-04-24","cited_by_count":0,"area":"safety"},{"id":"2604.25203","title":"BARRED: Synthetic Training of Custom Policy Guardrails via Asymmetric Debate","created":"2026-04-28","cited_by_count":0,"area":"safety"},{"id":"2605.05329","title":"Understanding Annotator Safety Policy with Interpretability","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2605.10901","title":"Beyond Red-Teaming: Formal Guarantees of LLM Guardrail Classifiers","created":"2026-05-11","cited_by_count":0,"area":"safety"}],"next_cursor":"100"}