{"total":59,"rows":[{"id":"2510.14276","title":"Qwen3Guard Technical Report","created":"2025-10-16","cited_by_count":155,"area":"safety"},{"id":"2601.10156","title":"ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and Feedback","created":"2026-01-15","cited_by_count":72,"area":"agents"},{"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":"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":"2604.18519","title":"LLM Safety From Within: Detecting Harmful Content with Internal Representations","created":"2026-04-20","cited_by_count":11,"area":"safety"},{"id":"2510.01146","title":"mR3: Multilingual Rubric-Agnostic Reward Reasoning Models","created":"2025-10-01","cited_by_count":8,"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":"2601.22136","title":"StepShield: When, Not Whether to Intervene on Rogue Agents","created":"2026-01-29","cited_by_count":7,"area":"safety"},{"id":"2601.19375","title":"Selective Steering: Norm-Preserving Control Through Discriminative Layer Selection","created":"2026-01-27","cited_by_count":6,"area":null},{"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":"2511.18852","title":"FanarGuard: A Culturally-Aware Moderation Filter for Arabic Language Models","created":"2025-11-24","cited_by_count":5,"area":null},{"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":"2605.17329","title":"LPG: Balancing Efficiency and Policy Reasoning in Latent Policy Guardrails","created":"2026-05-17","cited_by_count":5,"area":"lr"},{"id":"2604.03592","title":"Unveiling Language Routing Isolation in Multilingual MoE Models for Interpretable Subnetwork Adaptation","created":"2026-04-04","cited_by_count":4,"area":"moe"},{"id":"2605.07982","title":"GLiGuard: Schema-Conditioned Classification for LLM Safeguard","created":"2026-05-08","cited_by_count":4,"area":"safety"},{"id":"2602.00950","title":"MindGuard: Guardrail Classifiers for Multi-Turn Mental Health Support","created":"2026-02-01","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":"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":"2605.14454","title":"LiSA: Lifelong Safety Adaptation via Conservative Policy Induction","created":"2026-05-14","cited_by_count":3,"area":"safety"},{"id":"2606.01322","title":"TukaBench: A Culturally Grounded Jailbreak Benchmark for African Languages","created":"2026-05-31","cited_by_count":3,"area":"safety"},{"id":"2607.15550","title":"SeerGuard: A Safety Framework for Mobile GUI Agents via World Model Prediction","created":"2026-07-17","cited_by_count":3,"area":"wm"},{"id":"2507.05980","title":"Lost in Localization: Building RabakBench with Human-in-the-Loop Validation to Measure Multilingual Safety Gaps","created":"2025-07-08","cited_by_count":2,"area":"safety"},{"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":"2602.01618","title":"SEA-Guard: Culturally Grounded Multilingual Safeguard for Southeast Asia","created":"2026-02-02","cited_by_count":2,"area":null},{"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":"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":"2605.27489","title":"HARP: Measuring Harm Amplification in Multi-Agent LLM Systems","created":"2026-05-26","cited_by_count":2,"area":"agents"},{"id":"2605.29427","title":"FinGuard: Detecting Financial Regulatory Non-Compliance in LLM Interactions","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2606.01196","title":"Low-Resource Safety Failures Are Action Failures, Not Representation Failures","created":"2026-05-31","cited_by_count":2,"area":"alignment"},{"id":"2507.21782","title":"The Problem with Safety Classification is not just the Models","created":"2025-07-29","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":"2605.00689","title":"BabelSafe: A Policy-Grounded Multilingual Safety Benchmark for LLMs","created":"2026-05-01","cited_by_count":1,"area":"safety"},{"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":"2607.02079","title":"HaloGuard 1.0: An Open Weights Constitutional Classifier for Multilingual AI Safety","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2607.25857","title":"Shieldstral","created":"2026-07-28","cited_by_count":1,"area":null},{"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":"2509.14622","title":"Adversarial Distilled Retrieval-Augmented Guarding Model for Online Malicious Intent Detection","created":"2025-09-18","cited_by_count":0,"area":"rag"},{"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":"2605.27997","title":"Where Does Toxicity Live? Mechanistic Localization and Targeted Suppression in Language Models","created":"2026-05-27","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":"2606.03647","title":"All you need to break LLMs are Black-Box, Adapting, Efficient, Transferable, Harmful, Applicable ... Attacks","created":"2026-06-02","cited_by_count":0,"area":"safety"},{"id":"2606.06037","title":"SpeechJBB: Probing Safety Alignment and Comprehension in Large Audio Language Models under Code-Switched Speech","created":"2026-06-04","cited_by_count":0,"area":"alignment"},{"id":"2606.15396","title":"CHILLGuard: Towards Fine-Grained Chinese LLM Safety Guardrail with Scalable Data Construction and Model-aware Preference Alignment","created":"2026-06-13","cited_by_count":0,"area":"alignment"},{"id":"2606.25380","title":"A Survey of Toxicity Detection and Mitigation Strategies for Multilingual Language Models","created":"2026-06-24","cited_by_count":0,"area":"safety"},{"id":"2607.06326","title":"DT-Guard: Intent-Driven Reasoning-Active Training for Reasoning-Free LLM Safety Guardrail","created":"2026-07-07","cited_by_count":0,"area":"lr"},{"id":"2607.16215","title":"RAIL Guard: Closing the Evaluation-to-Remediation Gap in Responsible AI for LLM Agents","created":"2026-05-28","cited_by_count":0,"area":"agents"},{"id":"2608.01291","title":"ArabicDialectSafety: A Dialect-Aware Benchmark for Arabic Content Safety Classification","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2608.09551","title":"Pragmatic Attack Surface: Vulnerabilities of Implicit Context in Large Language Models","created":"2026-08-10","cited_by_count":0,"area":"alignment"},{"id":"2608.10621","title":"ProbGuard: Calibrated Safety Risk Estimation from LLM Output Distributions","created":"2026-08-11","cited_by_count":0,"area":"safety"},{"id":"2608.11905","title":"Policy-as-logic for robust reasoning over rules","created":"2026-08-12","cited_by_count":0,"area":"lr"},{"id":"2608.14626","title":"LLM Safety Alignment in Low-Resource Languages: A Systematic Literature Review","created":"2026-07-20","cited_by_count":0,"area":"alignment"},{"id":"2608.21775","title":"No One Model Catches Every Harm: Benchmarking Content Moderation Across Safety Scenarios","created":"2026-08-22","cited_by_count":0,"area":"safety"},{"id":"2608.27580","title":"LongGuard: Mechanistic Analysis and Training-Free Mitigation of Long-Context Failure in Safety Guardrails","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":"2609.01210","title":"Who Judges the Judges? A Chinese Safety QA Benchmark for Evaluating LLM Responses and Safety Judges","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.22144","title":"Multilingual Safety Signals Are Multi-Layered: Filtering Safety-Degrading Data for Safer LLMs","created":"2026-08-26","cited_by_count":0,"area":"alignment"},{"id":"2609.29266","title":"Baszta: Data-Centric Fine-Tuning of a Polish Multi-Label Safety Classifier","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.33634","title":"Safety Reconstructed: Generative Modeling via Masked Diffusion Builds Strong Safety Guardrails","created":"2026-09-27","cited_by_count":0,"area":"diffusion"},{"id":"2609.34415","title":"PROACT-Agent: Progressive Runtime Oversight and Active Circuit-breaking for Real-Time Safety","created":"2026-09-28","cited_by_count":0,"area":"agents"}],"next_cursor":null}