{"total":84,"rows":[{"id":"2410.07163","title":"Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning","created":"2024-10-09","cited_by_count":172,"area":"lr"},{"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":"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":"2407.10223","title":"On Large Language Model Continual Unlearning","created":"2024-07-14","cited_by_count":52,"area":"safety"},{"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":"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":"2408.10682","title":"Towards Robust Knowledge Unlearning: An Adversarial Framework for Assessing and Improving Unlearning Robustness in Large Language Models","created":"2024-08-20","cited_by_count":27,"area":"safety"},{"id":"2502.01083","title":"Tool Unlearning for Tool-Augmented LLMs","created":"2025-02-03","cited_by_count":17,"area":"agents"},{"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":"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":"2504.04626","title":"Exact Unlearning of Finetuning Data via Model Merging at Scale","created":"2025-04-06","cited_by_count":14,"area":"safety"},{"id":"2601.21571","title":"Shaping capabilities with token-level data filtering","created":"2026-01-29","cited_by_count":13,"area":null},{"id":"2505.22586","title":"Precise In-Parameter Concept Erasure in Large Language Models","created":"2025-05-28","cited_by_count":11,"area":null},{"id":"2506.06278","title":"Distillation Robustifies Unlearning","created":"2025-06-06","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":"2506.05314","title":"Constrained Entropic Unlearning: A Primal-Dual Framework for Large Language Models","created":"2025-06-05","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":"2506.00688","title":"Existing Large Language Model Unlearning Evaluations Are Inconclusive","created":"2025-05-31","cited_by_count":8,"area":"safety"},{"id":"2504.20185","title":"AI Supply Chains: An Emerging Ecosystem of AI Actors, Products, and Services","created":"2025-04-28","cited_by_count":7,"area":null},{"id":"2603.01285","title":"Attention Smoothing Is All You Need For Unlearning","created":"2026-03-01","cited_by_count":7,"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":"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":"2602.06441","title":"Is Gradient Ascent Really Necessary? Memorize to Forget for Machine Unlearning","created":"2026-02-06","cited_by_count":6,"area":"safety"},{"id":"2505.24379","title":"Unlearned but Not Forgotten: Data Extraction after Exact Unlearning in LLM","created":"2025-05-30","cited_by_count":5,"area":"safety"},{"id":"2509.22263","title":"Erase or Hide? Suppressing Spurious Unlearning Neurons for Robust Unlearning","created":"2025-09-26","cited_by_count":5,"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":"2509.24675","title":"Understanding the Dilemma of Unlearning for Large Language Models","created":"2025-09-29","cited_by_count":4,"area":"safety"},{"id":"2601.22313","title":"Hair-Trigger Alignment: Black-Box Evaluation Cannot Guarantee Post-Update Alignment","created":"2026-01-29","cited_by_count":4,"area":null},{"id":"2602.06248","title":"REBEL: Hidden Knowledge Recovery via Evolutionary-Based Evaluation Loop","created":"2026-02-05","cited_by_count":4,"area":"safety"},{"id":"2604.07962","title":"Is your algorithm unlearning or untraining?","created":"2026-04-09","cited_by_count":4,"area":"safety"},{"id":"2506.13181","title":"Align-then-Unlearn: Embedding Alignment for LLM Unlearning","created":"2025-06-16","cited_by_count":3,"area":"safety"},{"id":"2510.17620","title":"Forget to Know, Remember to Use: Context-Aware Unlearning for Large Language Models","created":"2025-10-20","cited_by_count":3,"area":"safety"},{"id":"2601.21283","title":"DUET: Distilled LLM Unlearning from an Efficiently Contextualized Teacher","created":"2026-01-29","cited_by_count":3,"area":"safety"},{"id":"2607.27539","title":"Can an AI Assistant Really Forget? Auditable Deletion from Addressable Memory","created":"2026-07-30","cited_by_count":3,"area":null},{"id":"2608.20442","title":"Stored in Optimizer State, Valued by Later Training: A Causal Account of Subliminal Trait Transfer","created":"2026-08-20","cited_by_count":3,"area":null},{"id":"2507.07754","title":"One-Point Contraction: Erasing Representational Separability toward Irreversible Deep Forgetting","created":"2025-07-10","cited_by_count":2,"area":"safety"},{"id":"2510.03263","title":"Memory Self-Regeneration: Uncovering Hidden Knowledge in Unlearned Models","created":"2025-09-26","cited_by_count":2,"area":"safety"},{"id":"2602.06911","title":"TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering","created":"2026-02-06","cited_by_count":2,"area":"safety"},{"id":"2606.03291","title":"Multilingual Unlearning in LLMs: Transfer, Dynamics, and Reversibility","created":"2026-06-02","cited_by_count":2,"area":"safety"},{"id":"2607.02513","title":"LACUNA: A Testbed for Evaluating Localization Precision for LLM Unlearning","created":"2026-07-02","cited_by_count":2,"area":"safety"},{"id":"2504.06407","title":"Understanding Machine Unlearning Through the Lens of Mode Connectivity","created":"2025-04-08","cited_by_count":1,"area":"safety"},{"id":"2509.20230","title":"Beyond Sharp Minima: Robust LLM Unlearning via Feedback-Guided Multi-Point Optimization","created":"2025-09-24","cited_by_count":1,"area":"safety"},{"id":"2510.17000","title":"Bits Leaked per Query: Information-Theoretic Bounds on Adversarial Attacks against LLMs","created":"2025-10-19","cited_by_count":1,"area":"safety"},{"id":"2512.11325","title":"Robust MLLM Unlearning via Visual Knowledge Distillation","created":"2025-12-12","cited_by_count":1,"area":"safety"},{"id":"2601.21702","title":"Beyond Forgetting: Representation Misdirection Elicits Controllable Side Behaviors and Capabilities","created":"2026-01-29","cited_by_count":1,"area":"safety"},{"id":"2602.03379","title":"Rethinking Benign Relearning: Syntax as the Hidden Driver of Unlearning Failures","created":"2026-02-03","cited_by_count":1,"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":"2603.00823","title":"A Comprehensive Evaluation of LLM Unlearning Robustness under Multi-Turn Interaction","created":"2026-02-28","cited_by_count":1,"area":"safety"},{"id":"2604.00430","title":"Secure Forgetting: A Framework for Privacy-Driven Unlearning in Large Language Model (LLM)-Based Agents","created":"2026-04-01","cited_by_count":1,"area":"lr"},{"id":"2605.11685","title":"Robust LLM Unlearning Against Relearning Attacks: The Minor Components in Representations Matter","created":"2026-05-12","cited_by_count":1,"area":"safety"},{"id":"2608.05783","title":"GROM: Gradient-Free Rapid One-Shot Machine Unlearning","created":"2026-08-06","cited_by_count":1,"area":"safety"},{"id":"2601.21682","title":"FIT to Forget: Robust Continual Unlearning for Large Language Models","created":"2026-01-29","cited_by_count":0,"area":"safety"},{"id":"2602.02139","title":"EvoMU: Evolutionary Machine Unlearning","created":"2026-02-02","cited_by_count":0,"area":"safety"},{"id":"2603.00133","title":"You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models","created":"2026-02-23","cited_by_count":0,"area":"diffusion"},{"id":"2604.00324","title":"The Persistent Vulnerability of Aligned AI Systems","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.06154","title":"Exclusive Unlearning","created":"2026-04-07","cited_by_count":0,"area":"safety"},{"id":"2604.13438","title":"WIN-U: Woodbury-Informed Newton-Unlearning as a retain-free Machine Unlearning Framework","created":"2026-04-15","cited_by_count":0,"area":"safety"},{"id":"2605.01699","title":"Probe-Geometry Alignment: Erasing the Cross-Sequence Memorization Signature Below Chance","created":"2026-05-03","cited_by_count":0,"area":"safety"},{"id":"2605.07482","title":"SHRED: Retain-Set-Free Unlearning via Self-Distillation with Logit Demotion","created":"2026-05-08","cited_by_count":0,"area":"safety"},{"id":"2605.10777","title":"Locking Pretrained Weights via Deep Low-Rank Residual Distillation","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.27138","title":"ICCU: In-Context Continual Unlearning via Pattern-Induced Refusal Rules","created":"2026-05-26","cited_by_count":0,"area":"safety"},{"id":"2605.30514","title":"MAAT: Multi-phase Adapter-Aware Targeted Unlearning","created":"2026-05-28","cited_by_count":0,"area":"safety"},{"id":"2606.18767","title":"Output Vector Editing for Memorization Mitigation in Large Language Models","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2606.29832","title":"The Forgetting-Retention Dilemma: Certified Unlearning Theory in Continual Learning","created":"2026-06-29","cited_by_count":0,"area":"safety"},{"id":"2606.30788","title":"Revocable Learned State via Process Sidecars","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.05407","title":"Position: Preventing AI-Generated CSAM Necessitates New Approaches to AI Safety","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2607.18615","title":"Stochastic Meta-Unlearning: Bridging Language Backbone and Multimodal Unlearning","created":"2026-07-21","cited_by_count":0,"area":"mllm"},{"id":"2607.23970","title":"Understanding Machine Unlearning Through the Lens of Mode Connectivity","created":"2026-07-27","cited_by_count":0,"area":"safety"},{"id":"2608.27782","title":"Memorization Is Not Extraction: Tight Differential-Privacy Bounds and Audit Blind Spots","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2608.29943","title":"On the Recoverability of Private Information Unlearning in Large Language Models","created":"2026-08-30","cited_by_count":0,"area":"safety"},{"id":"2609.03662","title":"Extracting Forgotten Prompts from Targeted Unlearned Models","created":"2026-09-03","cited_by_count":0,"area":"safety"},{"id":"2609.06872","title":"Exact Record Omission in Delta Attention: A Transport Criterion, Its Cost, and a Replay Certificate","created":"2026-09-06","cited_by_count":0,"area":null},{"id":"2609.21996","title":"A Lie Detector Test for Language Models: Reading Knowledge a Model Won't Reveal","created":"2026-09-18","cited_by_count":0,"area":"safety"},{"id":"2609.33559","title":"Fine Until Fine-Tuned: Repeated Solutions Make Reasoning Fragile","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.34591","title":"TULIP: Targeted LLM Unlearning at Layers Identified Per-Input","created":"2026-09-28","cited_by_count":0,"area":"safety"},{"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":"2609.37858","title":"Storage Is Not Strategy: State-Conditioned Support Control for LLM Unlearning","created":"2026-09-29","cited_by_count":0,"area":"safety"},{"id":"2609.38379","title":"Aligned Data Can Induce Misalignment via Context Confusion","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38909","title":"Unlearning Deceptive Behaviors in LLMs with Contrastive Forget Sets","created":"2026-09-30","cited_by_count":0,"area":"safety"},{"id":"2609.39279","title":"Faithful Dual-constrained Erasure for Robust LLM Safety Alignment","created":"2026-09-30","cited_by_count":0,"area":"alignment"},{"id":"2609.39866","title":"Preemptive LLM Unlearning against Forbidden Capability Acquisition via Gradient Sealing","created":"2026-09-30","cited_by_count":0,"area":"safety"},{"id":"2610.02418","title":"Mitigating Private Data Leakage in LLMs with Whiteout","created":"2026-10-01","cited_by_count":0,"area":"safety"},{"id":"2610.19385","title":"RA$^2$: Retain-Anchored Attraction Preserves Forget-Adjacent Utility in LLM Unlearning","created":"2026-10-14","cited_by_count":0,"area":"safety"}],"next_cursor":null}