{"total":65,"rows":[{"id":"2406.07933","title":"Large Language Model Unlearning via Embedding-Corrupted Prompts","created":"2024-06-12","cited_by_count":116,"area":"safety"},{"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":"2507.11878","title":"LLMs Encode Harmfulness and Refusal Separately","created":"2025-07-16","cited_by_count":88,"area":"safety"},{"id":"2406.02622","title":"Safeguarding Large Language Models: A Survey","created":"2024-06-03","cited_by_count":78,"area":"safety"},{"id":"2407.18369","title":"AI Safety in Generative AI Large Language Models: A Survey","created":"2024-07-06","cited_by_count":33,"area":null},{"id":"2505.16120","title":"LLM-Powered AI Agent Systems and Their Applications in Industry","created":"2025-05-22","cited_by_count":22,"area":"agents"},{"id":"2509.14284","title":"The Sum Leaks More Than Its Parts: Compositional Privacy Risks and Mitigations in Multi-Agent Collaboration","created":"2025-09-16","cited_by_count":20,"area":"agents"},{"id":"2502.05163","title":"Enhancing LLM Safety Through a Theoretical Minimax Game Lens","created":"2025-02-07","cited_by_count":19,"area":"safety"},{"id":"2509.02563","title":"DynaGuard: A Dynamic Guardian Model With User-Defined Policies","created":"2025-09-02","cited_by_count":19,"area":"safety"},{"id":"2602.11865","title":"Intelligent AI Delegation","created":"2026-02-12","cited_by_count":18,"area":null},{"id":"2603.22868","title":"Agent-Sentry: Bounding LLM Agents via Execution Provenance","created":"2026-03-24","cited_by_count":15,"area":"agents"},{"id":"2408.02205","title":"Swiss Cheese Model for AI Safety: A Taxonomy and Reference Architecture for Multi-Layered Guardrails of Foundation Model Based Agents","created":"2024-08-05","cited_by_count":14,"area":"agents"},{"id":"2501.13080","title":"Refining Input Guardrails: Enhancing LLM-as-a-Judge Efficiency Through Chain-of-Thought Fine-Tuning and Alignment","created":"2025-01-22","cited_by_count":14,"area":"lr"},{"id":"2509.23994","title":"Policy-as-Prompt: Turning AI Governance Rules into Guardrails for AI Agents","created":"2025-09-28","cited_by_count":14,"area":"safety"},{"id":"2407.18322","title":"The Need for Guardrails with Large Language Models in Medical Safety-Critical Settings: An Artificial Intelligence Application in the Pharmacovigilance Ecosystem","created":"2024-07-01","cited_by_count":11,"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":"2408.08959","title":"Trust-Oriented Adaptive Guardrails for Large Language Models","created":"2024-08-16","cited_by_count":8,"area":"safety"},{"id":"2601.07263","title":"When Bots Take the Bait: Exposing and Mitigating the Emerging Social Engineering Attack in Web Automation Agent","created":"2026-01-12","cited_by_count":7,"area":"agents"},{"id":"2405.12604","title":"Tiny Refinements Elicit Resilience: Toward Efficient Prefix-Model Against LLM Red-Teaming","created":"2024-05-21","cited_by_count":6,"area":"safety"},{"id":"2408.01452","title":"Building a Domain-specific Guardrail Model in Production","created":"2024-07-24","cited_by_count":6,"area":"safety"},{"id":"2501.03266","title":"LLM Content Moderation and User Satisfaction: Evidence from Response Refusals in Chatbot Arena","created":"2025-01-04","cited_by_count":6,"area":"safety"},{"id":"2502.19537","title":"No, of Course I Can! Deeper Fine-Tuning Attacks That Bypass Token-Level Safety Mechanisms","created":"2025-02-26","cited_by_count":6,"area":"safety"},{"id":"2508.13465","title":"LM Agents May Fail to Act on Their Own Risk Knowledge","created":"2025-08-19","cited_by_count":6,"area":"agents"},{"id":"2409.11393","title":"LLM-Agent-UMF: LLM-based Agent Unified Modeling Framework for Seamless Design of Multi Active/Passive Core-Agent Architectures","created":"2024-09-17","cited_by_count":5,"area":"agents"},{"id":"2411.04291","title":"Layer-wise Alignment: Examining Safety Alignment Across Image Encoder Layers in Vision Language Models","created":"2024-11-06","cited_by_count":4,"area":"mllm"},{"id":"2502.16174","title":"Efficient LLM Moderation with Multi-Layer Latent Prototypes","created":"2025-02-22","cited_by_count":4,"area":"safety"},{"id":"2509.08380","title":"Co-Investigator AI: The Rise of Agentic AI for Smarter, Trustworthy AML Compliance Narratives","created":"2025-09-10","cited_by_count":4,"area":"agents"},{"id":"2509.16444","title":"Domain-Specific Constitutional AI: Enhancing Safety in LLM-Powered Mental Health Chatbots","created":"2025-09-19","cited_by_count":4,"area":null},{"id":"2512.17375","title":"AdvJudge-Zero: Binary Decision Flips in LLM-as-a-Judge via Adversarial Control Tokens","created":"2025-12-19","cited_by_count":4,"area":"alignment"},{"id":"2501.08243","title":"Engineering LLM Powered Multi-agent Framework for Autonomous CloudOps","created":"2025-01-14","cited_by_count":3,"area":"agents"},{"id":"2508.15610","title":"Transduction is All You Need for Structured Data Workflows","created":"2025-08-21","cited_by_count":3,"area":"agents"},{"id":"2512.23547","title":"Lie to Me: Knowledge Graphs for Robust Hallucination Self-Detection in LLMs","created":"2025-12-29","cited_by_count":3,"area":null},{"id":"2605.10990","title":"Skill Drift Is Contract Violation: Proactive Maintenance for LLM Agent Skill Libraries","created":"2026-05-09","cited_by_count":3,"area":"agents"},{"id":"2502.11006","title":"Prompt Inject Detection with Generative Explanation as an Investigative Tool","created":"2025-02-16","cited_by_count":2,"area":"safety"},{"id":"2507.20503","title":"Customize Multi-modal RAI Guardrails with Precedent-based predictions","created":"2025-07-28","cited_by_count":2,"area":"safety"},{"id":"2508.16325","title":"ConceptGuard: Neuro-Symbolic Safety Guardrails via Sparse Interpretable Jailbreak Concepts","created":"2025-08-22","cited_by_count":2,"area":"safety"},{"id":"2601.19051","title":"Proactive Hardening of LLM Defenses with HASTE","created":"2026-01-27","cited_by_count":2,"area":"safety"},{"id":"2605.06901","title":"Reflections and New Directions for Human-Centered Large Language Models","created":"2026-05-07","cited_by_count":2,"area":null},{"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":"2406.16455","title":"Guardrails for avoiding harmful medical product recommendations and off-label promotion in generative AI models","created":"2024-06-24","cited_by_count":1,"area":"safety"},{"id":"2411.14442","title":"AI Ethics by Design: Implementing Customizable Guardrails for Responsible AI Development","created":"2024-11-05","cited_by_count":1,"area":null},{"id":"2507.03620","title":"Is It Time To Treat Prompts As Code? A Multi-Use Case Study For Prompt Optimization Using DSPy","created":"2025-07-04","cited_by_count":1,"area":"safety"},{"id":"2510.13727","title":"From Refusal to Recovery: A Control-Theoretic Approach to Generative AI Guardrails","created":"2025-10-15","cited_by_count":1,"area":"safety"},{"id":"2601.03300","title":"TRYLOCK: Defense-in-Depth Against LLM Jailbreaks via Layered Preference and Representation Engineering","created":"2026-01-06","cited_by_count":1,"area":"alignment"},{"id":"2603.22260","title":"Greater accessibility can amplify discrimination in generative AI","created":"2026-03-23","cited_by_count":1,"area":null},{"id":"2604.11666","title":"Playing Along: Learning a Double-Agent Defender for Belief Steering via Theory of Mind","created":"2026-04-13","cited_by_count":1,"area":"agents"},{"id":"2605.19035","title":"Trustworthy Agent Network: Trust in Agent Networks Must Be Baked In, Not Bolted On","created":"2026-05-18","cited_by_count":1,"area":"agents"},{"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":"2405.01858","title":"SUKHSANDESH: An Avatar Therapeutic Question Answering Platform for Sexual Education in Rural India","created":"2024-05-03","cited_by_count":0,"area":null},{"id":"2407.12812","title":"Building Understandable Messaging for Policy and Evidence Review (BUMPER) with AI","created":"2024-06-27","cited_by_count":0,"area":null},{"id":"2411.16730","title":"\"Moralized\" Multi-Step Jailbreak Prompts: Black-Box Testing of Guardrails in Large Language Models for Verbal Attacks","created":"2024-11-23","cited_by_count":0,"area":"safety"},{"id":"2412.04029","title":"Considerations Influencing Offense-Defense Dynamics From Artificial Intelligence","created":"2024-12-05","cited_by_count":0,"area":null},{"id":"2503.15512","title":"Policy alone is probably not the solution: A large-scale experiment on how developers struggle to design meaningful end-user explanations","created":"2025-01-28","cited_by_count":0,"area":null},{"id":"2511.21438","title":"Conversational No-code, Multi-agentic Disease Module Identification and Drug Repurposing Prediction with ChatDRex","created":"2025-11-26","cited_by_count":0,"area":"agents"},{"id":"2602.06650","title":"Beyond Static Alignment: Hierarchical Policy Control for LLM Safety via Risk-Aware Chain-of-Thought","created":"2026-02-06","cited_by_count":0,"area":"lr"},{"id":"2604.01504","title":"Magic, Madness, Heaven, Sin: LLM Output Diversity is Everything, Everywhere, All at Once","created":"2026-04-02","cited_by_count":0,"area":null},{"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":"2605.26942","title":"Neuro-Symbolic Verification of LLM Outputs for Data-Sensitive Domains (extended preprint)","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2607.21180","title":"Safeguards for Speech2Speech LLM-Assistants: A Case Study in Automotive Applications","created":"2026-07-23","cited_by_count":0,"area":"safety"},{"id":"2607.28137","title":"Asymmetric Communication: Large Language Models and Language Games","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.03361","title":"The Evolutionary Origin of Values: implications for AI alignment, sentience and existential risk","created":"2026-08-04","cited_by_count":0,"area":"alignment"},{"id":"2608.08471","title":"Yesterday's Shield, Today's Spear: A Self-Evolving Safety Guardrail in Production","created":"2026-08-09","cited_by_count":0,"area":"synth"},{"id":"2608.20378","title":"Truth Lies Deep: Countering Semantic Camouflage via Latent Intent Verification","created":"2026-06-27","cited_by_count":0,"area":"alignment"},{"id":"2610.01282","title":"Trustworthy Data- and ML-Ops for Intelligent Transportation Systems and Logistics","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.08923","title":"AdaGuard: Enhancing Safety and Policy Compliance with Reasoning-Enabled LLM-As-A-Judge Guardrails","created":"2026-10-06","cited_by_count":0,"area":"lr"}],"next_cursor":null}