{"total":163,"rows":[{"id":"2403.03218","title":"The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning","created":"2024-03-05","cited_by_count":509,"area":"safety"},{"id":"2404.05868","title":"Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning","created":"2024-04-08","cited_by_count":504,"area":"alignment"},{"id":"2407.06460","title":"MUSE: Machine Unlearning Six-Way Evaluation for Language Models","created":"2024-07-08","cited_by_count":261,"area":"safety"},{"id":"2407.15549","title":"Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs","created":"2024-07-22","cited_by_count":173,"area":"safety"},{"id":"2410.07163","title":"Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning","created":"2024-10-09","cited_by_count":172,"area":"lr"},{"id":"2408.15221","title":"LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet","created":"2024-08-27","cited_by_count":151,"area":"safety"},{"id":"2406.07358","title":"AI Sandbagging: Language Models can Strategically Underperform on Evaluations","created":"2024-06-11","cited_by_count":145,"area":null},{"id":"2408.00761","title":"Tamper-Resistant Safeguards for Open-Weight LLMs","created":"2024-08-01","cited_by_count":138,"area":"safety"},{"id":"2510.09023","title":"The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections","created":"2025-10-10","cited_by_count":129,"area":"safety"},{"id":"2409.18025","title":"An Adversarial Perspective on Machine Unlearning for AI Safety","created":"2024-09-26","cited_by_count":123,"area":"safety"},{"id":"2407.02646","title":"A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models","created":"2024-07-02","cited_by_count":118,"area":"mechinterp"},{"id":"2406.07933","title":"Large Language Model Unlearning via Embedding-Corrupted Prompts","created":"2024-06-12","cited_by_count":116,"area":"safety"},{"id":"2404.18239","title":"SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning","created":"2024-04-28","cited_by_count":104,"area":"safety"},{"id":"2403.03329","title":"Guardrail Baselines for Unlearning in LLMs","created":"2024-03-05","cited_by_count":96,"area":"safety"},{"id":"2404.15146","title":"Rethinking LLM Memorization through the Lens of Adversarial Compression","created":"2024-04-23","cited_by_count":94,"area":"lr"},{"id":"2406.13356","title":"Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearning","created":"2024-06-19","cited_by_count":84,"area":"safety"},{"id":"2506.12618","title":"OpenUnlearning: Accelerating LLM Unlearning via Unified Benchmarking of Methods and Metrics","created":"2025-06-14","cited_by_count":83,"area":"safety"},{"id":"2410.16454","title":"Catastrophic Failure of LLM Unlearning via Quantization","created":"2024-10-21","cited_by_count":81,"area":"safety"},{"id":"2502.05374","title":"Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond","created":"2025-02-07","cited_by_count":79,"area":"safety"},{"id":"2406.10890","title":"RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models","created":"2024-06-16","cited_by_count":78,"area":"safety"},{"id":"2410.08827","title":"Do Unlearning Methods Remove Information from Language Model Weights?","created":"2024-10-11","cited_by_count":73,"area":"safety"},{"id":"2410.02879","title":"Position: LLM Unlearning Benchmarks are Weak Measures of Progress","created":"2024-10-03","cited_by_count":63,"area":"safety"},{"id":"2412.17686","title":"Large Language Model Safety: A Holistic Survey","created":"2024-12-23","cited_by_count":59,"area":"safety"},{"id":"2407.17817","title":"Demystifying Verbatim Memorization in Large Language Models","created":"2024-07-25","cited_by_count":56,"area":null},{"id":"2407.10264","title":"What Makes and Breaks Safety Fine-tuning? A Mechanistic Study","created":"2024-07-14","cited_by_count":55,"area":"safety"},{"id":"2407.00106","title":"UnUnlearning: Unlearning is not sufficient for content regulation in advanced generative AI","created":"2024-06-27","cited_by_count":51,"area":"safety"},{"id":"2407.20516","title":"Machine Unlearning in Generative AI: A Survey","created":"2024-07-30","cited_by_count":49,"area":"safety"},{"id":"2405.19550","title":"Stress-Testing Capability Elicitation With Password-Locked Models","created":"2024-05-29","cited_by_count":46,"area":null},{"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":"2403.13682","title":"Threats, Attacks, and Defenses in Machine Unlearning: A Survey","created":"2024-03-20","cited_by_count":39,"area":"safety"},{"id":"2502.05209","title":"Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities","created":"2025-02-03","cited_by_count":39,"area":null},{"id":"2407.16997","title":"Revisiting Who's Harry Potter: Towards Targeted Unlearning from a Causal Intervention Perspective","created":"2024-07-24","cited_by_count":36,"area":"safety"},{"id":"2410.12949","title":"Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization","created":"2024-10-16","cited_by_count":35,"area":"safety"},{"id":"2410.02760","title":"Erasing Conceptual Knowledge from Language Models","created":"2024-10-03","cited_by_count":34,"area":"safety"},{"id":"2503.01854","title":"A Comprehensive Survey of Machine Unlearning Techniques for Large Language Models","created":"2025-02-22","cited_by_count":34,"area":"safety"},{"id":"2408.06223","title":"On Effects of Steering Latent Representation for Large Language Model Unlearning","created":"2024-08-12","cited_by_count":32,"area":"safety"},{"id":"2504.01550","title":"Representation Bending for Large Language Model Safety","created":"2025-04-02","cited_by_count":30,"area":"safety"},{"id":"2406.11614","title":"Intrinsic Test of Unlearning Using Parametric Knowledge Traces","created":"2024-06-17","cited_by_count":29,"area":"safety"},{"id":"2406.09179","title":"Towards Effective Evaluations and Comparisons for LLM Unlearning Methods","created":"2024-06-13","cited_by_count":27,"area":"safety"},{"id":"2410.17509","title":"WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models","created":"2024-10-23","cited_by_count":26,"area":"safety"},{"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":"2506.08164","title":"BLUR: A Bi-Level Optimization Approach for LLM Unlearning","created":"2025-06-09","cited_by_count":23,"area":"safety"},{"id":"2410.03523","title":"A Probabilistic Perspective on Unlearning and Alignment for Large Language Models","created":"2024-10-04","cited_by_count":21,"area":"alignment"},{"id":"2411.02631","title":"Extracting Unlearned Information from LLMs with Activation Steering","created":"2024-11-04","cited_by_count":21,"area":"safety"},{"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":"2404.05264","title":"Unbridled Icarus: A Survey of the Potential Perils of Image Inputs in Multimodal Large Language Model Security","created":"2024-04-08","cited_by_count":19,"area":"mllm"},{"id":"2410.17194","title":"Representation Shattering in Transformers: A Synthetic Study with Knowledge Editing","created":"2024-10-22","cited_by_count":19,"area":null},{"id":"2412.06370","title":"Exploring Memorization and Copyright Violation in Frontier LLMs: A Study of the New York Times v. OpenAI 2023 Lawsuit","created":"2024-12-09","cited_by_count":18,"area":null},{"id":"2502.01083","title":"Tool Unlearning for Tool-Augmented LLMs","created":"2025-02-03","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":"2510.19422","title":"LLM Unlearning with LLM Beliefs","created":"2025-10-22","cited_by_count":17,"area":"safety"},{"id":"2502.11441","title":"Which Retain Set Matters for LLM Unlearning? A Case Study on Entity Unlearning","created":"2025-02-17","cited_by_count":16,"area":"safety"},{"id":"2410.17050","title":"UnStar: Unlearning with Self-Taught Anti-Sample Reasoning for LLMs","created":"2024-10-22","cited_by_count":15,"area":"lr"},{"id":"2412.06966","title":"Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Research","created":"2024-12-09","cited_by_count":15,"area":"safety"},{"id":"2502.02260","title":"Position: Adversarial ML for LLMs Is Not Making Any Progress","created":"2025-02-04","cited_by_count":15,"area":null},{"id":"2506.15699","title":"BLUR: A Benchmark for LLM Unlearning Robust to Forget-Retain Overlap","created":"2025-05-28","cited_by_count":15,"area":"safety"},{"id":"2406.15796","title":"Unveiling Entity-Level Unlearning for Large Language Models: A Comprehensive Analysis","created":"2024-06-22","cited_by_count":14,"area":"safety"},{"id":"2410.15153","title":"Evaluating Deep Unlearning in Large Language Models","created":"2024-10-19","cited_by_count":14,"area":"safety"},{"id":"2502.17823","title":"A General Framework to Enhance Fine-tuning-based LLM Unlearning","created":"2025-02-25","cited_by_count":14,"area":"safety"},{"id":"2503.14530","title":"SAUCE: Selective Concept Unlearning in Vision-Language Models with Sparse Autoencoders","created":"2025-03-16","cited_by_count":13,"area":"mllm"},{"id":"2601.21571","title":"Shaping capabilities with token-level data filtering","created":"2026-01-29","cited_by_count":13,"area":null},{"id":"2504.10185","title":"LLM Unlearning Reveals a Stronger-Than-Expected Coreset Effect in Current Benchmarks","created":"2025-04-14","cited_by_count":12,"area":"safety"},{"id":"2505.01456","title":"Unlearning Sensitive Information in Multimodal LLMs: Benchmark and Attack-Defense Evaluation","created":"2025-05-01","cited_by_count":11,"area":"mllm"},{"id":"2505.16559","title":"CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-Tuning","created":"2025-05-22","cited_by_count":11,"area":"safety"},{"id":"2506.06278","title":"Distillation Robustifies Unlearning","created":"2025-06-06","cited_by_count":11,"area":"safety"},{"id":"2506.09227","title":"SoK: Machine Unlearning for Large Language Models","created":"2025-06-10","cited_by_count":11,"area":"safety"},{"id":"2506.14003","title":"Unlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model Outputs","created":"2025-06-16","cited_by_count":11,"area":"safety"},{"id":"2508.13650","title":"CRISP: Persistent Concept Unlearning via Sparse Autoencoders","created":"2025-08-19","cited_by_count":11,"area":"safety"},{"id":"2512.05648","title":"Beyond Data Filtering: Knowledge Localization for Capability Removal in LLMs","created":"2025-12-05","cited_by_count":11,"area":"safety"},{"id":"2405.15523","title":"The Mosaic Memory of Large Language Models","created":"2024-05-24","cited_by_count":10,"area":null},{"id":"2408.16961","title":"The Future of Open Human Feedback","created":"2024-08-15","cited_by_count":10,"area":"alignment"},{"id":"2502.00406","title":"Agents Are All You Need for LLM Unlearning","created":"2025-02-01","cited_by_count":10,"area":"agents"},{"id":"2505.16252","title":"Does Localization Inform Unlearning? A Rigorous Examination of Local Parameter Attribution for Knowledge Unlearning in Language Models","created":"2025-05-22","cited_by_count":10,"area":"safety"},{"id":"2501.19202","title":"Improving LLM Unlearning Robustness via Random Perturbations","created":"2025-01-31","cited_by_count":9,"area":"safety"},{"id":"2502.17323","title":"When to Forget? Complexity Trade-offs in Machine Unlearning","created":"2025-02-24","cited_by_count":9,"area":"safety"},{"id":"2506.00359","title":"Keeping an Eye on LLM Unlearning: The Hidden Risk and Remedy","created":"2025-05-31","cited_by_count":9,"area":"safety"},{"id":"2506.04410","title":"Matter-of-Fact: A Benchmark for Verifying the Feasibility of Literature-Supported Claims in Materials Science","created":"2025-06-04","cited_by_count":9,"area":null},{"id":"2506.00688","title":"Existing Large Language Model Unlearning Evaluations Are Inconclusive","created":"2025-05-31","cited_by_count":8,"area":"safety"},{"id":"2507.21084","title":"Reviving Your MNEME: Predicting The Side Effects of LLM Unlearning and Fine-Tuning via Sparse Model Diffing","created":"2025-06-19","cited_by_count":8,"area":"safety"},{"id":"2505.23270","title":"Does Machine Unlearning Truly Remove Knowledge?","created":"2025-05-29","cited_by_count":7,"area":"safety"},{"id":"2507.04219","title":"Model Collapse Is Not a Bug but a Feature in Machine Unlearning for LLMs","created":"2025-07-06","cited_by_count":7,"area":"synth"},{"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":"2603.09980","title":"Explainable LLM Unlearning Through Reasoning","created":"2026-02-08","cited_by_count":7,"area":"lr"},{"id":"2605.18891","title":"Auditing Reasoning-Trace Memorization Claims after Unlearning with Head-Conditioned Canaries","created":"2026-05-17","cited_by_count":7,"area":"lr"},{"id":"2502.19207","title":"FaithUn: Toward Faithful Forgetting in Language Models by Investigating the Interconnectedness of Knowledge","created":"2025-02-26","cited_by_count":6,"area":"safety"},{"id":"2506.03142","title":"Not All Tokens Are Meant to Be Forgotten","created":"2025-06-03","cited_by_count":6,"area":"safety"},{"id":"2506.17279","title":"Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models","created":"2025-06-14","cited_by_count":6,"area":"lr"},{"id":"2507.20140","title":"Do Not Mimic My Voice: Speaker Identity Unlearning for Zero-Shot Text-to-Speech","created":"2025-07-27","cited_by_count":6,"area":"safety"},{"id":"2510.16629","title":"On the Impossibility of Retrain Equivalence in Machine Unlearning","created":"2025-10-18","cited_by_count":6,"area":"safety"},{"id":"2510.17021","title":"Forgetting to Forget: Attention Sink as A Gateway for Backdooring LLM Unlearning","created":"2025-10-19","cited_by_count":6,"area":"safety"},{"id":"2505.14832","title":"SEPS: A Separability Measure for Robust Unlearning in LLMs","created":"2025-05-20","cited_by_count":5,"area":"safety"},{"id":"2506.10236","title":"Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods","created":"2025-06-11","cited_by_count":5,"area":"safety"},{"id":"2510.12981","title":"Reference-Specific Unlearning Metrics Can Hide the Truth: A Reality Check","created":"2025-10-14","cited_by_count":5,"area":"safety"},{"id":"2407.06483","title":"Composable Interventions for Language Models","created":"2024-07-09","cited_by_count":4,"area":"safety"},{"id":"2408.10608","title":"BTBR: A Bayesian-Theory-Driven Probabilistic-Fuzzy Framework for Implicit Bias Removal in Large Language Models","created":"2024-08-20","cited_by_count":4,"area":null},{"id":"2411.04388","title":"Unlearning in- vs. out-of-distribution data in LLMs under gradient-based method","created":"2024-11-07","cited_by_count":4,"area":"safety"},{"id":"2503.01986","title":"Adaptively profiling models with task elicitation","created":"2025-03-03","cited_by_count":4,"area":null},{"id":"2505.15209","title":"DUSK: Do Not Unlearn Shared Knowledge","created":"2025-05-21","cited_by_count":4,"area":"safety"},{"id":"2506.01318","title":"Unlearning's Blind Spots: Over-Unlearning and Prototypical Relearning Attack","created":"2025-06-02","cited_by_count":4,"area":"safety"},{"id":"2506.12484","title":"Robust LLM Unlearning with MUDMAN: Meta-Unlearning with Disruption Masking And Normalization","created":"2025-06-14","cited_by_count":4,"area":"safety"}],"next_cursor":"100"}