{"total":51,"rows":[{"id":"2402.08787","title":"Rethinking Machine Unlearning for Large Language Models","created":"2024-02-13","cited_by_count":257,"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":"2401.01286","title":"A Comprehensive Study of Knowledge Editing for Large Language Models","created":"2024-01-02","cited_by_count":163,"area":null},{"id":"2409.18025","title":"An Adversarial Perspective on Machine Unlearning for AI Safety","created":"2024-09-26","cited_by_count":123,"area":"safety"},{"id":"2403.05030","title":"Defending Against Unforeseen Failure Modes with Latent Adversarial Training","created":"2024-03-08","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":"2406.10328","title":"From Pixels to Prose: A Large Dataset of Dense Image Captions","created":"2024-06-14","cited_by_count":54,"area":"mllm"},{"id":"2505.16831","title":"Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMs","created":"2025-05-22","cited_by_count":42,"area":"safety"},{"id":"2502.07218","title":"LLM Unlearning via Neural Activation Redirection","created":"2025-02-11","cited_by_count":41,"area":"safety"},{"id":"2402.12343","title":"Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!","created":"2024-02-19","cited_by_count":37,"area":"alignment"},{"id":"2410.08811","title":"PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning","created":"2024-10-11","cited_by_count":33,"area":"safety"},{"id":"2506.11094","title":"The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMs","created":"2025-06-06","cited_by_count":26,"area":null},{"id":"2406.05392","title":"Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Survey","created":"2024-06-08","cited_by_count":23,"area":null},{"id":"2506.08164","title":"BLUR: A Bi-Level Optimization Approach for LLM Unlearning","created":"2025-06-09","cited_by_count":23,"area":"safety"},{"id":"2506.09996","title":"From Judgment to Interference: Early Stopping LLM Harmful Outputs via Streaming Content Monitoring","created":"2025-06-11","cited_by_count":22,"area":"alignment"},{"id":"2506.01339","title":"Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning","created":"2025-06-02","cited_by_count":21,"area":"safety"},{"id":"2401.10647","title":"Sowing the Wind, Reaping the Whirlwind: The Impact of Editing Language Models","created":"2024-01-19","cited_by_count":20,"area":"safety"},{"id":"2411.14133","title":"GASP: Efficient Black-Box Generation of Adversarial Suffixes for Jailbreaking LLMs","created":"2024-11-21","cited_by_count":12,"area":"safety"},{"id":"2509.02820","title":"Unlearning That Lasts: Utility-Preserving, Robust, and Almost Irreversible Forgetting in LLMs","created":"2025-09-02","cited_by_count":11,"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":"2410.01106","title":"Statistical inference on black-box generative models in the data kernel perspective space","created":"2024-10-01","cited_by_count":9,"area":null},{"id":"2501.19202","title":"Improving LLM Unlearning Robustness via Random Perturbations","created":"2025-01-31","cited_by_count":9,"area":"safety"},{"id":"2508.05775","title":"Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM","created":"2025-08-07","cited_by_count":9,"area":"alignment"},{"id":"2511.04934","title":"Leak@$k$: Unlearning Does Not Make LLMs Forget Under Probabilistic Decoding","created":"2025-11-07","cited_by_count":9,"area":"safety"},{"id":"2506.01790","title":"IF-GUIDE: Influence Function-Guided Detoxification of LLMs","created":"2025-06-02","cited_by_count":7,"area":null},{"id":"2603.02913","title":"Eliciting Numerical Predictive Distributions of LLMs Without Autoregression","created":"2026-03-03","cited_by_count":6,"area":null},{"id":"2411.07858","title":"Verbosity $\\neq$ Veracity: Demystify Verbosity Compensation Behavior of Large Language Models","created":"2024-11-12","cited_by_count":5,"area":null},{"id":"2503.13390","title":"Aligned Probing: Relating Toxic Behavior and Model Internals","created":"2025-03-17","cited_by_count":5,"area":null},{"id":"2512.19025","title":"The Erasure Illusion: Stress-Testing the Generalization of LLM Forgetting Evaluation","created":"2025-12-22","cited_by_count":5,"area":"safety"},{"id":"2412.06843","title":"Semantic Loss Guided Data Efficient Supervised Fine Tuning for Safe Responses in LLMs","created":"2024-12-07","cited_by_count":4,"area":null},{"id":"2504.21299","title":"BiasGuard: A Reasoning-enhanced Bias Detection Tool For Large Language Models","created":"2025-04-30","cited_by_count":4,"area":"lr"},{"id":"2505.17089","title":"Chain-of-Thought Driven Adversarial Scenario Extrapolation for Robust Language Models","created":"2025-05-20","cited_by_count":4,"area":"lr"},{"id":"2509.25271","title":"RADAR: A Risk-Aware Dynamic Multi-Agent Framework for LLM Safety Evaluation via Role-Specialized Collaboration","created":"2025-09-28","cited_by_count":4,"area":"agents"},{"id":"2411.05172","title":"ImpScore: A Learnable Metric For Quantifying The Implicitness Level of Sentence","created":"2024-11-07","cited_by_count":3,"area":null},{"id":"2505.04578","title":"Fight Fire with Fire: Defending Against Malicious RL Fine-Tuning via Reward Neutralization","created":"2025-05-07","cited_by_count":3,"area":"safety"},{"id":"2509.25539","title":"Toxicity in Online Platforms and AI Systems: A Survey of Needs, Challenges, Mitigations, and Future Directions","created":"2025-09-29","cited_by_count":3,"area":null},{"id":"2412.11145","title":"The Superalignment of Superhuman Intelligence with Large Language Models","created":"2024-12-15","cited_by_count":2,"area":"mllm"},{"id":"2510.09007","title":"LLM Unlearning on Noisy Forget Sets: A Study of Incomplete, Rewritten, and Watermarked Data","created":"2025-10-10","cited_by_count":2,"area":"safety"},{"id":"2602.08901","title":"Mitigating Memorization Where It Happens","created":"2026-02-09","cited_by_count":2,"area":null},{"id":"2605.16776","title":"Distinguishable Deletion: Unifying Knowledge Erasure and Refusal for Large Language Model Unlearning","created":"2026-05-16","cited_by_count":2,"area":"safety"},{"id":"2602.23391","title":"Detoxifying LLMs via Representation Erasure-Based Preference Optimization","created":"2026-02-24","cited_by_count":1,"area":"alignment"},{"id":"2508.09997","title":"Thematic and Task-Based Categorization of K-12 GenAI Usages with Hierarchical Topic Modeling","created":"2025-08-01","cited_by_count":0,"area":null},{"id":"2510.02194","title":"UpSafe$^\\circ$C: Upcycling for Controllable Safety in Large Language Models","created":"2025-10-02","cited_by_count":0,"area":"moe"},{"id":"2601.05260","title":"Quantifying Document Impact in RAG-LLMs","created":"2025-10-27","cited_by_count":0,"area":"rag"},{"id":"2601.13122","title":"Responsible AI for General-Purpose Systems: Overview, Challenges, and A Path Forward","created":"2026-01-19","cited_by_count":0,"area":null},{"id":"2602.22146","title":"Provable Last-Iterate Convergence for Multi-Objective Safe LLM Alignment via Optimistic Primal-Dual","created":"2026-02-25","cited_by_count":0,"area":"alignment"},{"id":"2605.14087","title":"Measuring and Mitigating Toxicity in Large Language Models: A Comprehensive Replication Study","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.18879","title":"ZeroUnlearn: Few-Shot Knowledge Unlearning in Large Language Models","created":"2026-05-16","cited_by_count":0,"area":"safety"},{"id":"2605.23974","title":"AERIC: Anticipatory Hidden-State Monitoring for Implicit Harmful Dialogue","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2609.36612","title":"Do LLMs Really Forget? Hidden-State Leakage in Model Unlearning and How to Fix it","created":"2026-09-29","cited_by_count":0,"area":"safety"},{"id":"2609.37076","title":"UnlearningSoup: Is Repeated Tuning Necessary for Large Language Model Unlearning?","created":"2026-09-29","cited_by_count":0,"area":"safety"}],"next_cursor":null}