{"total":59,"rows":[{"id":"2502.00640","title":"CollabLLM: From Passive Responders to Active Collaborators","created":"2025-02-02","cited_by_count":124,"area":null},{"id":"2504.15585","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","created":"2025-04-22","cited_by_count":116,"area":"lr"},{"id":"2504.17704","title":"Safety in Large Reasoning Models: A Survey","created":"2025-04-24","cited_by_count":64,"area":"lr"},{"id":"2508.13220","title":"MCPSecBench: A Systematic Security Benchmark and Playground for Testing Model Context Protocols","created":"2025-08-17","cited_by_count":51,"area":"agents"},{"id":"2506.07022","title":"AlphaSteer: Learning Refusal Steering with Principled Null-Space Constraint","created":"2025-06-08","cited_by_count":49,"area":"safety"},{"id":"2505.24119","title":"The State of Multilingual LLM Safety Research: From Measuring the Language Gap to Mitigating It","created":"2025-05-30","cited_by_count":45,"area":"safety"},{"id":"2506.13666","title":"We Should Identify and Mitigate Third-Party Safety Risks in MCP-Powered Agent Systems","created":"2025-06-16","cited_by_count":27,"area":"agents"},{"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":"2505.14667","title":"SAFEPATH: Preventing Harmful Reasoning in Chain-of-Thought via Early Alignment","created":"2025-05-20","cited_by_count":24,"area":"lr"},{"id":"2505.10924","title":"A Survey on the Safety and Security Threats of Computer-Using Agents: JARVIS or Ultron?","created":"2025-05-16","cited_by_count":23,"area":"agents"},{"id":"2511.10262","title":"MTR-DuplexBench: Towards a Comprehensive Evaluation of Multi-Round Conversations for Full-Duplex Speech Language Models","created":"2025-11-13","cited_by_count":22,"area":null},{"id":"2511.05993","title":"Revisiting Entropy in Reinforcement Learning for Large Reasoning Models","created":"2025-11-08","cited_by_count":21,"area":"lr"},{"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":"2510.19422","title":"LLM Unlearning with LLM Beliefs","created":"2025-10-22","cited_by_count":17,"area":"safety"},{"id":"2507.22168","title":"Persona-Augmented Benchmarking: Evaluating LLMs Across Diverse Writing Styles","created":"2025-07-29","cited_by_count":16,"area":null},{"id":"2512.02445","title":"When Refusals Fail: Unstable Safety Mechanisms in Long-Context LLM Agents","created":"2025-12-02","cited_by_count":15,"area":"agents"},{"id":"2502.15865","title":"Standard Benchmarks Fail -- Auditing LLM Agents in Finance Must Prioritize Risk","created":"2025-02-21","cited_by_count":13,"area":"agents"},{"id":"2502.05240","title":"Survey on AI-Generated Media Detection: From Non-MLLM to MLLM","created":"2025-02-07","cited_by_count":12,"area":null},{"id":"2503.01742","title":"Building Safe GenAI Applications: An End-to-End Overview of Red Teaming for Large Language Models","created":"2025-03-03","cited_by_count":11,"area":"safety"},{"id":"2506.05451","title":"Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety","created":"2025-06-05","cited_by_count":10,"area":"safety"},{"id":"2505.11926","title":"SafeVid: Toward Safety Aligned Video Large Multimodal Models","created":"2025-05-17","cited_by_count":9,"area":"mllm"},{"id":"2510.05691","title":"DecEx-RAG: Boosting Agentic Retrieval-Augmented Generation with Decision and Execution Optimization via Process Supervision","created":"2025-10-07","cited_by_count":9,"area":"rag"},{"id":"2504.10615","title":"Beyond Chains of Thought: Benchmarking Latent-Space Reasoning Abilities in Large Language Models","created":"2025-04-14","cited_by_count":6,"area":"lr"},{"id":"2506.12263","title":"A Survey of Foundation Models for IoT: Taxonomy and Criteria-Based Analysis","created":"2025-06-13","cited_by_count":5,"area":null},{"id":"2605.16746","title":"State Contamination in Memory-Augmented LLM Agents","created":"2026-05-16","cited_by_count":5,"area":"agents"},{"id":"2506.17111","title":"Are Bias Evaluation Methods Biased ?","created":"2025-06-20","cited_by_count":4,"area":null},{"id":"2511.06778","title":"SAFENLIDB: A Privacy-Preserving Safety Alignment Framework for LLM-based Natural Language Database Interfaces","created":"2025-11-10","cited_by_count":4,"area":"alignment"},{"id":"2602.11136","title":"FormalJudge: A Neuro-Symbolic Paradigm for Agentic Oversight","created":"2026-02-11","cited_by_count":4,"area":"agents"},{"id":"2604.00304","title":"Asymmetric Actor-Critic for Multi-turn LLM Agents","created":"2026-03-31","cited_by_count":4,"area":"lr"},{"id":"2510.08158","title":"Beyond Over-Refusal: Scenario-Based Diagnostics and Post-Hoc Mitigation for Exaggerated Refusals in LLMs","created":"2025-10-09","cited_by_count":3,"area":"safety"},{"id":"2511.01187","title":"Surfacing Subtle Stereotypes: A Multilingual, Debate-Oriented Evaluation of Modern LLMs","created":"2025-11-03","cited_by_count":3,"area":null},{"id":"2511.22924","title":"MAS-Shield: A Defense Framework for Secure and Efficient LLM MAS","created":"2025-11-28","cited_by_count":3,"area":null},{"id":"2604.25011","title":"Why Does Reinforcement Learning Generalize? A Feature-Level Mechanistic Study of Post-Training in Large Language Models","created":"2026-04-27","cited_by_count":3,"area":"lr"},{"id":"2602.08901","title":"Mitigating Memorization Where It Happens","created":"2026-02-09","cited_by_count":2,"area":null},{"id":"2602.19275","title":"KUDA: Knowledge Unlearning by Deviating Representation for Large Language Models","created":"2026-02-22","cited_by_count":2,"area":"safety"},{"id":"2603.01792","title":"ALTER: Asymmetric LoRA for Token-Entropy-Guided Unlearning of LLMs","created":"2026-03-02","cited_by_count":2,"area":"safety"},{"id":"2604.18775","title":"An Empirical Study of Multi-Generation Sampling for Jailbreak Detection in Large Language Models","created":"2026-04-20","cited_by_count":2,"area":"safety"},{"id":"2608.28327","title":"Layered LLM Defenses as an Ensemble: Access Tiers, Inference Cost, and the Measured Failure Correlation Between Defense Layers","created":"2026-08-28","cited_by_count":2,"area":null},{"id":"2601.08668","title":"Analyzing Bias in False Refusal Behavior of Large Language Models for Hate Speech Detoxification","created":"2026-01-13","cited_by_count":1,"area":null},{"id":"2601.12033","title":"Preserving Fairness and Safety in Quantized LLMs Through Critical Weight Protection","created":"2026-01-17","cited_by_count":1,"area":null},{"id":"2602.02600","title":"Step-Wise Refusal Dynamics in Autoregressive and Diffusion Language Models","created":"2026-02-01","cited_by_count":1,"area":"diffusion"},{"id":"2602.06440","title":"TrailBlazer: History-Guided Reinforcement Learning for Black-Box LLM Jailbreaking","created":"2026-02-06","cited_by_count":1,"area":"safety"},{"id":"2603.09434","title":"Common Sense vs. Morality: The Curious Case of Narrative Focus Bias in LLMs","created":"2026-03-10","cited_by_count":1,"area":null},{"id":"2603.20581","title":"JUBAKU: An Adversarial Benchmark for Exposing Culturally Grounded Stereotypes in Japanese LLMs","created":"2026-03-21","cited_by_count":1,"area":null},{"id":"2604.12601","title":"LLM-Guided Prompt Evolution for Password Guessing","created":"2026-04-14","cited_by_count":1,"area":null},{"id":"2510.03520","title":"Certifiable Safe RLHF: Semantic Grounding and Fixed Penalty Constraint Optimization for Safer LLM Alignment","created":"2025-10-03","cited_by_count":0,"area":"alignment"},{"id":"2510.27628","title":"Validity Is What You Need","created":"2025-10-31","cited_by_count":0,"area":"agents"},{"id":"2512.02043","title":"Mirror, Mirror on the Wall -- Which is the Best Model of Them All?","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2512.20649","title":"AIAuditTrack: A Framework for AI Security system","created":"2025-12-16","cited_by_count":0,"area":null},{"id":"2512.24263","title":"Constrained Language Model Policy Optimization via Risk-aware Stepwise Alignment","created":"2025-12-30","cited_by_count":0,"area":"alignment"},{"id":"2604.27550","title":"APPSI-139: A Parallel Corpus of English Application Privacy Policy Summarization and Interpretation","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2606.09038","title":"Personalization Meets Safety:Mechanisms,Risks,and Mitigations in Personalized LLMs","created":"2026-06-08","cited_by_count":0,"area":"moe"},{"id":"2608.10530","title":"On Understanding, Identifying, and Mitigating Vulnerabilities in Agentic Large Language Models","created":"2026-08-11","cited_by_count":0,"area":"agents"},{"id":"2608.20355","title":"ExpertIVS: Sociological Expert Driven Individual Value Simulation in Large Language Models","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2608.23020","title":"Unlearning Is Not Just Erasing: Temporal Decoupling via Generation Inequality","created":"2026-08-24","cited_by_count":0,"area":"safety"},{"id":"2608.30197","title":"ALTSTEER: Selective Safety Steering for Moving Beyond Hard Refusals to Constructive Alternatives","created":"2026-08-31","cited_by_count":0,"area":"alignment"},{"id":"2609.00728","title":"SOVER: Formal Certification of Optimization Reformulations via LLM-Assisted SMT Verification","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.27763","title":"Alignment of LRMs via Counter-Aligned Few-Shot Conversation Exposure","created":"2026-08-16","cited_by_count":0,"area":"lr"},{"id":"2609.38036","title":"Gender bias across LLMs is common and highly heterogeneous","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}