{"total":72,"rows":[{"id":"2402.08787","title":"Rethinking Machine Unlearning for Large Language Models","created":"2024-02-13","cited_by_count":257,"area":"lr"},{"id":"2410.04070","title":"PAD: Personalized Alignment of LLMs at Decoding-Time","created":"2024-10-05","cited_by_count":60,"area":"alignment"},{"id":"2402.11846","title":"UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models","created":"2024-02-19","cited_by_count":50,"area":"diffusion"},{"id":"2405.12523","title":"Single Image Unlearning: Efficient Machine Unlearning in Multimodal Large Language Models","created":"2024-05-21","cited_by_count":46,"area":"mllm"},{"id":"2409.19732","title":"Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement","created":"2024-09-29","cited_by_count":45,"area":"safety"},{"id":"2403.07362","title":"Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearning","created":"2024-03-12","cited_by_count":44,"area":"safety"},{"id":"2504.14492","title":"FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering","created":"2025-04-20","cited_by_count":40,"area":"mechinterp"},{"id":"2410.19317","title":"FairMT-Bench: Benchmarking Fairness for Multi-turn Dialogue in Conversational LLMs","created":"2024-10-25","cited_by_count":36,"area":null},{"id":"2402.14015","title":"Corrective Machine Unlearning","created":"2024-02-21","cited_by_count":29,"area":"safety"},{"id":"2405.10989","title":"Learnable Privacy Neurons Localization in Language Models","created":"2024-05-16","cited_by_count":27,"area":null},{"id":"2410.15334","title":"Modality-Fair Preference Optimization for Trustworthy MLLM Alignment","created":"2024-10-20","cited_by_count":26,"area":"mllm"},{"id":"2405.17814","title":"FAIntbench: A Holistic and Precise Benchmark for Bias Evaluation in Text-to-Image Models","created":"2024-05-28","cited_by_count":22,"area":null},{"id":"2407.10241","title":"BiasAlert: A Plug-and-play Tool for Social Bias Detection in LLMs","created":"2024-07-14","cited_by_count":21,"area":null},{"id":"2311.12047","title":"MultiDelete for Multimodal Machine Unlearning","created":"2023-11-18","cited_by_count":20,"area":"safety"},{"id":"2403.08994","title":"Ethos: Rectifying Language Models in Orthogonal Parameter Space","created":"2024-03-13","cited_by_count":20,"area":null},{"id":"2407.10494","title":"Learning to Unlearn for Robust Machine Unlearning","created":"2024-07-15","cited_by_count":19,"area":"safety"},{"id":"2507.18100","title":"Datasets and Recipes for Video Temporal Grounding via Reinforcement Learning","created":"2025-07-24","cited_by_count":19,"area":"lr"},{"id":"2406.14796","title":"MU-Bench: A Multitask Multimodal Benchmark for Machine Unlearning","created":"2024-06-21","cited_by_count":17,"area":"safety"},{"id":"2405.09341","title":"Large Language Model Bias Mitigation from the Perspective of Knowledge Editing","created":"2024-05-15","cited_by_count":16,"area":null},{"id":"2406.04997","title":"On the social bias of speech self-supervised models","created":"2024-06-07","cited_by_count":16,"area":null},{"id":"2412.07808","title":"Boosting Alignment for Post-Unlearning Text-to-Image Generative Models","created":"2024-12-09","cited_by_count":15,"area":"diffusion"},{"id":"2408.11843","title":"Identifying and Mitigating Social Bias Knowledge in Language Models","created":"2024-08-07","cited_by_count":13,"area":null},{"id":"2503.18314","title":"LoTUS: Large-Scale Machine Unlearning with a Taste of Uncertainty","created":"2025-03-24","cited_by_count":13,"area":"safety"},{"id":"2405.17462","title":"Ferrari: Federated Feature Unlearning via Optimizing Feature Sensitivity","created":"2024-05-23","cited_by_count":11,"area":"safety"},{"id":"2504.12574","title":"ForgetMe: Evaluating Selective Forgetting in Generative Models","created":"2025-04-17","cited_by_count":11,"area":"diffusion"},{"id":"2504.12663","title":"Persona-judge: Personalized Alignment of Large Language Models via Token-level Self-judgment","created":"2025-04-17","cited_by_count":11,"area":"alignment"},{"id":"2410.01276","title":"Deep Unlearn: Benchmarking Machine Unlearning for Image Classification","created":"2024-10-02","cited_by_count":9,"area":"safety"},{"id":"2411.11667","title":"Dissecting Representation Misalignment in Contrastive Learning via Influence Function","created":"2024-11-18","cited_by_count":8,"area":null},{"id":"2406.13551","title":"Mitigating Social Biases in Language Models through Unlearning","created":"2024-06-19","cited_by_count":7,"area":"safety"},{"id":"2502.10407","title":"Addressing Bias in Generative AI: Challenges and Research Opportunities in Information Management","created":"2025-01-22","cited_by_count":7,"area":null},{"id":"2502.12430","title":"Position: Bridge the Gaps between Machine Unlearning and AI Regulation","created":"2025-02-18","cited_by_count":7,"area":"safety"},{"id":"2408.14393","title":"CURE4Rec: A Benchmark for Recommendation Unlearning with Deeper Influence","created":"2024-08-26","cited_by_count":6,"area":"safety"},{"id":"2412.16780","title":"Forget Vectors at Play: Universal Input Perturbations Driving Machine Unlearning in Image Classification","created":"2024-12-21","cited_by_count":6,"area":"safety"},{"id":"2505.08576","title":"MUBox: A Critical Evaluation Framework of Deep Machine Unlearning","created":"2025-05-13","cited_by_count":6,"area":"safety"},{"id":"2505.23829","title":"BiasFilter: An Inference-Time Debiasing Framework for Large Language Models","created":"2025-05-28","cited_by_count":6,"area":null},{"id":"2508.15127","title":"Towards Source-Free Machine Unlearning","created":"2025-08-20","cited_by_count":6,"area":"safety"},{"id":"2509.25673","title":"Mitigating Biases in Language Models via Bias Unlearning","created":"2025-09-30","cited_by_count":6,"area":"safety"},{"id":"2601.05641","title":"Multilingual Amnesia: On the Transferability of Unlearning in Multilingual LLMs","created":"2026-01-09","cited_by_count":6,"area":"safety"},{"id":"2503.04240","title":"DiffPO: Diffusion-styled Preference Optimization for Efficient Inference-Time Alignment of Large Language Models","created":"2025-03-06","cited_by_count":5,"area":"alignment"},{"id":"2505.15700","title":"\"Alexa, can you forget me?\" Machine Unlearning Benchmark in Spoken Language Understanding","created":"2025-05-21","cited_by_count":5,"area":"safety"},{"id":"2410.23693","title":"Zero-shot Class Unlearning via Layer-wise Relevance Analysis and Neuronal Path Perturbation","created":"2024-10-31","cited_by_count":4,"area":"safety"},{"id":"2405.16798","title":"Exploring Fairness in Educational Data Mining in the Context of the Right to be Forgotten","created":"2024-05-27","cited_by_count":3,"area":"safety"},{"id":"2408.13438","title":"Explainable Concept Generation through Vision-Language Preference Learning for Understanding Neural Networks' Internal Representations","created":"2024-08-24","cited_by_count":3,"area":null},{"id":"2410.10120","title":"Evaluating of Machine Unlearning: Robustness Verification Without Prior Modifications","created":"2024-10-14","cited_by_count":3,"area":"safety"},{"id":"2503.09330","title":"Group-robust Machine Unlearning","created":"2025-03-12","cited_by_count":3,"area":"safety"},{"id":"2408.10468","title":"Tracing Privacy Leakage of Language Models to Training Data via Adjusted Influence Functions","created":"2024-08-20","cited_by_count":2,"area":null},{"id":"2409.05208","title":"Influence-based Attributions can be Manipulated","created":"2024-09-08","cited_by_count":2,"area":null},{"id":"2502.16708","title":"Exploring Incremental Unlearning: Techniques, Challenges, and Future Directions","created":"2025-02-23","cited_by_count":2,"area":"safety"},{"id":"2507.20284","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","created":"2025-07-27","cited_by_count":2,"area":null},{"id":"2509.15723","title":"REFER: Mitigating Bias in Opinion Summarisation via Frequency Framed Prompting","created":"2025-09-19","cited_by_count":2,"area":null},{"id":"2602.08901","title":"Mitigating Memorization Where It Happens","created":"2026-02-09","cited_by_count":2,"area":null},{"id":"2410.08069","title":"Unlearning-based Neural Interpretations","created":"2024-10-10","cited_by_count":1,"area":"safety"},{"id":"2501.14182","title":"Single-weight Model Editing for Post-hoc Spurious Correlation Neutralization","created":"2025-01-24","cited_by_count":1,"area":null},{"id":"2502.01669","title":"Delayed Feedback Modeling with Influence Functions","created":"2025-02-01","cited_by_count":1,"area":null},{"id":"2506.12527","title":"Detection, Classification, and Mitigation of Gender Bias in Large Language Models","created":"2025-06-14","cited_by_count":1,"area":null},{"id":"2509.16400","title":"'Rich Dad, Poor Lad': How do Large Language Models Contextualize Socioeconomic Factors in College Admission ?","created":"2025-09-19","cited_by_count":1,"area":null},{"id":"2512.03068","title":"ECHO: A Participatory Framework for Bias-Anchored AI Harm Anticipation","created":"2025-11-27","cited_by_count":1,"area":null},{"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":"2608.00622","title":"A Heuristic Perspective on Debiasing Language Models","created":"2026-08-01","cited_by_count":1,"area":null},{"id":"2410.06446","title":"Machine Unlearning in Forgettability Sequence","created":"2024-10-09","cited_by_count":0,"area":"safety"},{"id":"2502.06398","title":"Learning Counterfactual Outcomes Under Rank Preservation","created":"2025-02-10","cited_by_count":0,"area":null},{"id":"2504.08616","title":"Preserving Privacy Without Compromising Accuracy: Machine Unlearning for Handwritten Text Recognition","created":"2025-04-11","cited_by_count":0,"area":"safety"},{"id":"2505.14945","title":"Unlearning Algorithmic Biases over Graphs","created":"2025-05-20","cited_by_count":0,"area":"safety"},{"id":"2505.18783","title":"Soft Weighted Machine Unlearning","created":"2025-05-24","cited_by_count":0,"area":"safety"},{"id":"2507.10886","title":"How to Protect Models against Adversarial Unlearning?","created":"2025-07-15","cited_by_count":0,"area":"safety"},{"id":"2507.17984","title":"Machine Unlearning of Traffic State Estimation and Prediction","created":"2025-07-23","cited_by_count":0,"area":"safety"},{"id":"2508.18826","title":"SWiFT: Soft-Mask Weight Fine-tuning for Bias Mitigation","created":"2025-08-26","cited_by_count":0,"area":null},{"id":"2509.07456","title":"Bias-Aware Machine Unlearning: Towards Fairer Vision Models via Controllable Forgetting","created":"2025-09-09","cited_by_count":0,"area":"safety"},{"id":"2510.19226","title":"Controllable Machine Unlearning via Gradient Pivoting","created":"2025-10-22","cited_by_count":0,"area":"safety"},{"id":"2511.00854","title":"TriCon-Fair: Triplet Contrastive Learning for Mitigating Social Bias in Pre-trained Language Models","created":"2025-11-02","cited_by_count":0,"area":null},{"id":"2605.19042","title":"Interference-Aware Multi-Task Unlearning","created":"2026-05-18","cited_by_count":0,"area":"safety"},{"id":"2610.04310","title":"Modeling Deletion Requests in Machine Unlearning","created":"2026-10-03","cited_by_count":0,"area":"safety"}],"next_cursor":null}