{"total":175,"rows":[{"id":"2501.00663","title":"Titans: Learning to Memorize at Test Time","created":"2024-12-31","cited_by_count":328,"area":"lr"},{"id":"2404.18231","title":"From Persona to Personalization: A Survey on Role-Playing Language Agents","created":"2024-04-28","cited_by_count":212,"area":"agents"},{"id":"2409.00138","title":"PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action","created":"2024-08-29","cited_by_count":171,"area":null},{"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":"2405.03520","title":"Is Sora a World Simulator? A Comprehensive Survey on General World Models and Beyond","created":"2024-05-06","cited_by_count":111,"area":"wm"},{"id":"2310.11829","title":"Graph Foundation Models: Concepts, Opportunities and Challenges","created":"2023-10-18","cited_by_count":103,"area":null},{"id":"2311.06062","title":"Practical Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration","created":"2023-11-10","cited_by_count":98,"area":"safety"},{"id":"2503.09780","title":"AgentDAM: Privacy Leakage Evaluation for Autonomous Web Agents","created":"2025-03-12","cited_by_count":82,"area":"agents"},{"id":"2412.17686","title":"Large Language Model Safety: A Holistic Survey","created":"2024-12-23","cited_by_count":59,"area":"safety"},{"id":"2410.08109","title":"A Closer Look at Machine Unlearning for Large Language Models","created":"2024-10-10","cited_by_count":56,"area":"safety"},{"id":"2407.11438","title":"Trust No Bot: Discovering Personal Disclosures in Human-LLM Conversations in the Wild","created":"2024-07-16","cited_by_count":47,"area":null},{"id":"2311.04235","title":"Can LLMs Follow Simple Rules?","created":"2023-11-06","cited_by_count":46,"area":null},{"id":"2408.12787","title":"LLM-PBE: Assessing Data Privacy in Large Language Models","created":"2024-08-23","cited_by_count":41,"area":null},{"id":"2310.18362","title":"SoK: Memorization in General-Purpose Large Language Models","created":"2023-10-24","cited_by_count":37,"area":null},{"id":"2404.10618","title":"Private Attribute Inference from Images with Vision-Language Models","created":"2024-04-16","cited_by_count":37,"area":"mllm"},{"id":"2404.11045","title":"Offset Unlearning for Large Language Models","created":"2024-04-17","cited_by_count":36,"area":"safety"},{"id":"2406.07217","title":"A Synthetic Dataset for Personal Attribute Inference","created":"2024-06-11","cited_by_count":36,"area":"synth"},{"id":"2404.13968","title":"Protecting Your LLMs with Information Bottleneck","created":"2024-04-22","cited_by_count":29,"area":"safety"},{"id":"2405.10632","title":"Towards interactive evaluations for interaction harms in human-AI systems","created":"2024-05-17","cited_by_count":29,"area":null},{"id":"2602.08412","title":"From Assistant to Double Agent: Formalizing and Benchmarking Attacks on OpenClaw for Personalized Local AI Agent","created":"2026-02-09","cited_by_count":29,"area":"agents"},{"id":"2409.14457","title":"Large Model Based Agents: State-of-the-Art, Cooperation Paradigms, Security and Privacy, and Future Trends","created":"2024-09-22","cited_by_count":26,"area":null},{"id":"2410.07959","title":"COMPL-AI Framework: A Technical Interpretation and LLM Benchmarking Suite for the EU Artificial Intelligence Act","created":"2024-10-10","cited_by_count":24,"area":null},{"id":"2407.02956","title":"IncogniText: Privacy-enhancing Conditional Text Anonymization via LLM-based Private Attribute Randomization","created":"2024-07-03","cited_by_count":23,"area":null},{"id":"2402.13846","title":"Large Language Models are Advanced Anonymizers","created":"2024-02-21","cited_by_count":22,"area":null},{"id":"2407.13934","title":"Towards Trustworthy AI: A Review of Ethical and Robust Large Language Models","created":"2024-06-01","cited_by_count":22,"area":null},{"id":"2404.00750","title":"Can Language Models Recognize Convincing Arguments?","created":"2024-03-31","cited_by_count":21,"area":null},{"id":"2505.01976","title":"A Survey on Privacy Risks and Protection in Large Language Models","created":"2025-05-04","cited_by_count":21,"area":"safety"},{"id":"2505.18893","title":"Reality Check: A New Evaluation Ecosystem Is Necessary to Understand AI's Real World Effects","created":"2025-05-24","cited_by_count":19,"area":null},{"id":"2506.10922","title":"Robustly Improving LLM Fairness in Realistic Settings via Interpretability","created":"2025-06-12","cited_by_count":18,"area":null},{"id":"2402.14273","title":"Can Language Models Act as Knowledge Bases at Scale?","created":"2024-02-22","cited_by_count":17,"area":null},{"id":"2505.08807","title":"Security of Internet of Agents: Attacks and Countermeasures","created":"2025-05-12","cited_by_count":17,"area":"agents"},{"id":"2505.13312","title":"GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection","created":"2025-05-19","cited_by_count":17,"area":"safety"},{"id":"2510.01645","title":"Position: Privacy Is Not Just Memorization!","created":"2025-10-02","cited_by_count":17,"area":null},{"id":"2408.13247","title":"An In-Depth Investigation of Data Collection in LLM App Ecosystems","created":"2024-08-23","cited_by_count":14,"area":null},{"id":"2602.16800","title":"Large-scale online deanonymization with LLMs","created":"2026-02-18","cited_by_count":14,"area":null},{"id":"2405.20681","title":"No Free Lunch Theorem for Privacy-Preserving LLM Inference","created":"2024-05-31","cited_by_count":13,"area":null},{"id":"2406.11715","title":"Measuring memorization in RLHF for code completion","created":"2024-06-17","cited_by_count":13,"area":"alignment"},{"id":"2410.07582","title":"Detecting Training Data of Large Language Models via Expectation Maximization","created":"2024-10-10","cited_by_count":13,"area":"safety"},{"id":"2506.11680","title":"Malicious LLM-Based Conversational AI Makes Users Reveal Personal Information","created":"2025-06-13","cited_by_count":13,"area":null},{"id":"2405.17423","title":"Privacy-Aware Visual Language Models","created":"2024-05-27","cited_by_count":12,"area":"mllm"},{"id":"2408.07291","title":"Evaluating LLM-based Personal Information Extraction and Countermeasures","created":"2024-08-14","cited_by_count":12,"area":"safety"},{"id":"2410.02159","title":"Mitigating Memorization In Language Models","created":"2024-10-03","cited_by_count":12,"area":"safety"},{"id":"2502.14412","title":"Evaluating Precise Geolocation Inference Capabilities of Vision Language Models","created":"2025-02-20","cited_by_count":12,"area":"mllm"},{"id":"2402.12408","title":"ModelGPT: Unleashing LLM's Capabilities for Tailored Model Generation","created":"2024-02-18","cited_by_count":11,"area":null},{"id":"2506.12241","title":"Privacy Reasoning in Ambiguous Contexts","created":"2025-06-13","cited_by_count":11,"area":"lr"},{"id":"2512.16310","title":"Agent Tools Orchestration Leaks More: Dataset, Benchmark, and Mitigation","created":"2025-12-18","cited_by_count":11,"area":"agents"},{"id":"2601.20882","title":"DevOps-Gym: Benchmarking AI Agents in Software DevOps Cycle","created":"2026-01-27","cited_by_count":11,"area":null},{"id":"2502.00406","title":"Agents Are All You Need for LLM Unlearning","created":"2025-02-01","cited_by_count":10,"area":"agents"},{"id":"2502.15086","title":"Is Safety Standard Same for Everyone? User-Specific Safety Evaluation of Large Language Models","created":"2025-02-20","cited_by_count":10,"area":"safety"},{"id":"2505.09056","title":"A Comprehensive Analysis of Large Language Model Outputs: Similarity, Diversity, and Bias","created":"2025-05-14","cited_by_count":10,"area":null},{"id":"2507.05578","title":"The Landscape of Memorization in LLMs: Mechanisms, Measurement, and Mitigation","created":"2025-07-08","cited_by_count":10,"area":"safety"},{"id":"2502.19158","title":"When Personalization Meets Reality: A Multi-Faceted Analysis of Personalized Preference Learning","created":"2025-02-26","cited_by_count":9,"area":"alignment"},{"id":"2505.19139","title":"The Eye of Sherlock Holmes: Uncovering User Private Attribute Profiling via Vision-Language Model Agentic Framework","created":"2025-05-25","cited_by_count":9,"area":null},{"id":"2404.05783","title":"A Survey on Responsible Generative AI: What to Generate and What Not","created":"2024-04-08","cited_by_count":8,"area":null},{"id":"2510.03662","title":"Operationalizing Data Minimization for Privacy-Preserving LLM Prompting","created":"2025-10-04","cited_by_count":8,"area":null},{"id":"2503.02296","title":"Memorize or Generalize? Evaluating LLM Code Generation with Code Rewriting","created":"2025-03-04","cited_by_count":7,"area":null},{"id":"2509.00192","title":"Safe-LLaVA: A Privacy-Preserving Vision-Language Dataset and Benchmark for Biometric Safety","created":"2025-08-29","cited_by_count":7,"area":"mllm"},{"id":"2511.05784","title":"DRAGON: Guard LLM Unlearning in Context via Negative Detection and Reasoning","created":"2025-11-08","cited_by_count":7,"area":"lr"},{"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":"2403.16139","title":"A Little Leak Will Sink a Great Ship: Survey of Transparency for Large Language Models from Start to Finish","created":"2024-03-24","cited_by_count":6,"area":null},{"id":"2409.03274","title":"Recent Advances in Attack and Defense Approaches of Large Language Models","created":"2024-09-05","cited_by_count":6,"area":null},{"id":"2504.15827","title":"DualOptim: Enhancing Efficacy and Stability in Machine Unlearning with Dual Optimizers","created":"2025-04-22","cited_by_count":6,"area":"safety"},{"id":"2505.20910","title":"Automated Privacy Information Annotation in Large Language Model Interactions","created":"2025-05-27","cited_by_count":6,"area":null},{"id":"2507.04531","title":"DP-Fusion: Token-Level Differentially Private Inference for Large Language Models","created":"2025-07-06","cited_by_count":6,"area":"safety"},{"id":"2509.08653","title":"Generative Data Refinement: Just Ask for Better Data","created":"2025-09-10","cited_by_count":6,"area":null},{"id":"2509.14278","title":"Beyond Data Privacy: New Privacy Risks for Large Language Models","created":"2025-09-16","cited_by_count":6,"area":null},{"id":"2402.07812","title":"Retrieval Augmented Thought Process for Private Data Handling in Healthcare","created":"2024-02-12","cited_by_count":5,"area":"lr"},{"id":"2505.15805","title":"Keep Security! Benchmarking Security Policy Preservation in Large Language Model Contexts Against Indirect Attacks in Question Answering","created":"2025-05-21","cited_by_count":5,"area":null},{"id":"2509.08604","title":"Memorization in Large Language Models in Medicine: Prevalence, Characteristics, and Implications","created":"2025-09-10","cited_by_count":5,"area":null},{"id":"2311.17228","title":"Survey on AI Ethics: A Socio-technical Perspective","created":"2023-11-28","cited_by_count":4,"area":null},{"id":"2406.14549","title":"Uncovering Latent Memories: Assessing Data Leakage and Memorization Patterns in Frontier AI Models","created":"2024-06-20","cited_by_count":4,"area":null},{"id":"2411.13226","title":"AIDBench: A benchmark for evaluating the authorship identification capability of large language models","created":"2024-11-20","cited_by_count":4,"area":null},{"id":"2503.16586","title":"Big Help or Big Brother? Auditing Tracking, Profiling, and Personalization in Generative AI Assistants","created":"2025-03-20","cited_by_count":4,"area":null},{"id":"2505.14549","title":"Can Large Language Models Really Recognize Your Name?","created":"2025-05-20","cited_by_count":4,"area":null},{"id":"2506.01420","title":"Self-Refining Language Model Anonymizers via Adversarial Distillation","created":"2025-06-02","cited_by_count":4,"area":null},{"id":"2507.11128","title":"What Should LLMs Forget? Quantifying Personal Data in LLMs for Right-to-Be-Forgotten Requests","created":"2025-07-15","cited_by_count":4,"area":"safety"},{"id":"2507.16124","title":"Benchmarking LLM Privacy Recognition for Social Robot Decision Making","created":"2025-07-22","cited_by_count":4,"area":null},{"id":"2509.22483","title":"OFMU: Optimization-Driven Framework for Machine Unlearning","created":"2025-09-26","cited_by_count":4,"area":"safety"},{"id":"2510.00761","title":"Downgrade to Upgrade: Optimizer Simplification Enhances Robustness in LLM Unlearning","created":"2025-10-01","cited_by_count":4,"area":"safety"},{"id":"2512.16059","title":"ContextLeak: Auditing Leakage in Private In-Context Learning Methods","created":"2025-12-18","cited_by_count":4,"area":null},{"id":"2603.18382","title":"From Weak Cues to Real Identities: Evaluating Inference-Driven De-Anonymization in LLM Agents","created":"2026-03-19","cited_by_count":4,"area":"agents"},{"id":"2605.19127","title":"POLAR-Bench: A Diagnostic Benchmark for Privacy-Utility Trade-offs in LLM Agents","created":"2026-05-18","cited_by_count":4,"area":"agents"},{"id":"2410.13060","title":"AERO: Entropy-Guided Framework for Private LLM Inference","created":"2024-10-16","cited_by_count":3,"area":null},{"id":"2412.19496","title":"Multi-PA: A Multi-perspective Benchmark on Privacy Assessment for Large Vision-Language Models","created":"2024-12-27","cited_by_count":3,"area":"mllm"},{"id":"2502.06567","title":"Membership Inference Risks in Quantized Models: A Theoretical and Empirical Study","created":"2025-02-10","cited_by_count":3,"area":"safety"},{"id":"2503.12314","title":"Empirical Privacy Variance","created":"2025-03-16","cited_by_count":3,"area":null},{"id":"2505.15722","title":"Shared Path: Unraveling Memorization in Multilingual LLMs through Language Similarities","created":"2025-05-21","cited_by_count":3,"area":null},{"id":"2507.22930","title":"Protecting Vulnerable Voices: Synthetic Dataset Generation for Self-Disclosure Detection","created":"2025-07-24","cited_by_count":3,"area":"synth"},{"id":"2510.22376","title":"Label Smoothing Improves Gradient Ascent in LLM Unlearning","created":"2025-10-25","cited_by_count":3,"area":"safety"},{"id":"2602.11528","title":"Stop Tracking Me! Proactive Defense Against Attribute Inference Attack in LLMs","created":"2026-02-12","cited_by_count":3,"area":null},{"id":"2402.06922","title":"Whispers in the Machine: Confidentiality in Agentic Systems","created":"2024-02-10","cited_by_count":2,"area":"agents"},{"id":"2404.05047","title":"Initial Exploration of Zero-Shot Privacy Utility Tradeoffs in Tabular Data Using GPT-4","created":"2024-04-07","cited_by_count":2,"area":null},{"id":"2406.02481","title":"Large Language Models as Carriers of Hidden Messages","created":"2024-06-04","cited_by_count":2,"area":null},{"id":"2410.13138","title":"Data Defenses Against Large Language Models","created":"2024-10-17","cited_by_count":2,"area":null},{"id":"2411.03287","title":"The Future of Intelligent Healthcare: A Systematic Analysis and Discussion on the Integration and Impact of Robots Using Large Language Models for Healthcare","created":"2024-11-05","cited_by_count":2,"area":null},{"id":"2509.12152","title":"Beyond PII: How Users Attempt to Estimate and Mitigate Implicit LLM Inference","created":"2025-09-15","cited_by_count":2,"area":null},{"id":"2601.22440","title":"AI and My Values: User Perceptions of LLMs' Ability to Extract, Embody, and Explain Human Values from Casual Conversations","created":"2026-01-30","cited_by_count":2,"area":null},{"id":"2603.21573","title":"Rethinking Visual Privacy: A Compositional Privacy Risk Framework for Severity Assessment with VLMs","created":"2026-03-23","cited_by_count":2,"area":null},{"id":"2605.06901","title":"Reflections and New Directions for Human-Centered Large Language Models","created":"2026-05-07","cited_by_count":2,"area":null}],"next_cursor":"100"}