mlsanityData to 7 Oct 2026

Machine Unlearning in Generative AI: A Survey

arXiv 2407.20516 ↗First posted 30 Jul 2024cs.LG cs.AI cs.CLcited by 49

On the map: LLM safety and security → Machine unlearning

Abstract (arXiv)

Generative AI technologies have been deployed in many places, such as (multimodal) large language models and vision generative models. Their remarkable performance should be attributed to massive training data and emergent reasoning abilities. However, the models would memorize and generate sensitive, biased, or dangerous information originated from the training data especially those from web crawl. New machine unlearning (MU) techniques are being developed to reduce or eliminate undesirable knowledge and its effects from the models, because those that were designed for traditional classification tasks could not be applied for Generative AI. We offer a comprehensive survey on many things about MU in Generative AI, such as a new problem formulation, evaluation methods, and a structured discussion on the advantages and limitations of different kinds of MU techniques. It also presents several critical challenges and promising directions in MU research. A curated list of readings can be found: https://github.com/franciscoliu/GenAI-MU-Reading.

Key facts. Cited by 49 papers in the map (data through 7 Oct 2026). Placed in Machine unlearning, one of 12 directions in LLM safety and security. Builds on 126 of its 164 references that are in the map. First posted on arXiv 30 Jul 2024.

Builds on

126 of 164 references.

Closest ancestors · 28

Same direction, newest first

  1. 2024Avoiding Copyright Infringement via Large Language Model Unlearning16 Jun
  2. 2024Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning8 Apr
  3. 2024Digital Forgetting in Large Language Models: A Survey of Unlearning Methods2 Apr
  4. 2024Machine Unlearning for Traditional Models and Large Language Models: A Short Survey1 Apr
  5. 2024Threats, Attacks, and Defenses in Machine Unlearning: A Survey20 Mar
  6. 2024Guardrail Baselines for Unlearning in LLMs5 Mar
  7. 2024Dissecting Language Models: Machine Unlearning via Selective Pruning2 Mar
  8. 2024Eight Methods to Evaluate Robust Unlearning in LLMs26 Feb
  9. 2024Machine Unlearning of Pre-trained Large Language Models23 Feb
  10. 2024Towards Safer Large Language Models through Machine Unlearning15 Feb
  11. 2024UNDIAL: Self-Distillation with Adjusted Logits for Robust Unlearning in Large Language Models15 Feb
  12. 2024EFUF: Efficient Fine-grained Unlearning Framework for Mitigating Hallucinations in Multimodal Large Language Models15 Feb
16 more
  1. 2024Selective Forgetting: Advancing Machine Unlearning Techniques and Evaluation in Language Models8 Feb
  2. 2024TOFU: A Task of Fictitious Unlearning for LLMs11 Jan
  3. 2023FairSISA: Ensemble Post-Processing to Improve Fairness of Unlearning in LLMs12 Dec
  4. 2023Unlearn What You Want to Forget: Efficient Unlearning for LLMs31 Oct
  5. 2023Breaking the Trilemma of Privacy, Utility, Efficiency via Controllable Machine Unlearning28 Oct
  6. 2023SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation19 Oct
  7. 2023In-Context Unlearning: Language Models as Few Shot Unlearners11 Oct
  8. 2023Who's Harry Potter? Approximate Unlearning in LLMs3 Oct
  9. 2023Separate the Wheat from the Chaff: Model Deficiency Unlearning via Parameter-Efficient Module Operation16 Aug
  10. 2023KGA: A General Machine Unlearning Framework Based on Knowledge Gap Alignment11 May
  11. 2022Privacy Adhering Machine Un-learning in NLP19 Dec
  12. 2022Knowledge Unlearning for Mitigating Privacy Risks in Language Models4 Oct
  13. 2022Can Bad Teaching Induce Forgetting? Unlearning in Deep Networks using an Incompetent Teacher17 May
  14. 2021Unrolling SGD: Understanding Factors Influencing Machine Unlearning27 Sep
  15. 2021Hard to Forget: Poisoning Attacks on Certified Machine Unlearning17 Sep
  16. 2021Machine Unlearning of Features and Labels26 Aug

Other references · 98

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  6. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  7. 2023GPT-4 Technical Reportcited by 18,132
  8. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  9. 2022Training language models to follow instructions with human feedbackcited by 15,712
  10. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  11. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  12. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
38 more
  1. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  2. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  3. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,854
  4. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  5. 2023Improved Baselines with Visual Instruction Tuningcited by 4,362
  6. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  7. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  8. 2019HellaSwag: Can a Machine Really Finish Your Sentence?cited by 4,018
  9. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  10. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
  11. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,286
  12. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  13. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,919
  14. 2019PIQA: Reasoning about Physical Commonsense in Natural Languagecited by 2,818
  15. 2022Locating and Editing Factual Associations in GPTcited by 2,609
  16. 2020The Pile: An 800GB Dataset of Diverse Text for Language Modelingcited by 2,346
  17. 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,250
  18. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,231
  19. 2014Conditional Generative Adversarial Netscited by 2,152
  20. 2017Understanding Black-box Predictions via Influence Functionscited by 1,714
  21. 2023Jailbroken: How Does LLM Safety Training Fail?cited by 1,565
  22. 2022Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference timecited by 1,366
  23. 2017Continual Learning with Deep Generative Replaycited by 1,152
  24. 2023Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!cited by 1,106
  25. 2015Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Bookscited by 1,041
  26. 2019Machine Unlearningcited by 1,020
  27. 2023Training Diffusion Models with Reinforcement Learningcited by 939
  28. 2020StereoSet: Measuring stereotypical bias in pretrained language modelscited by 911
  29. 2022Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learningcited by 886
  30. 2023BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Datasetcited by 828
  31. 2018Personalizing Dialogue Agents: I have a dog, do you have pets too?cited by 820
  32. 2022Discovering Language Model Behaviors with Model-Written Evaluationscited by 805
  33. 2021Robust fine-tuning of zero-shot modelscited by 785
  34. 2021Deduplicating Training Data Makes Language Models Bettercited by 705
  35. 2020CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Modelscited by 703
  36. 2023Aligning Large Multimodal Models with Factually Augmented RLHFcited by 703
  37. 2018Object Hallucination in Image Captioningcited by 661
  38. 2019MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalismscited by 653

50 most cited of 98 All 98 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 7; 2025: 29; 2026: 13.

49 papers.

Sort:

By area:

  1. 2025A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deploymentcited by 110
  2. 2024Protecting Privacy in Multimodal Large Language Models with MLLMU-Benchcited by 61
  3. 2024Position: LLM Unlearning Benchmarks are Weak Measures of Progresscited by 58
  4. 2025A Comprehensive Survey of Machine Unlearning Techniques for Large Language Modelscited by 30
  5. 2024On Effects of Steering Latent Representation for Large Language Model Unlearningcited by 27
  6. 2025Modality-Aware Neuron Pruning for Unlearning in Multimodal Large Language Modelscited by 25
  7. 2024Towards Robust Knowledge Unlearning: An Adversarial Framework for Assessing and Improving Unlearning Robustness in Large Language Modelscited by 24
  8. 2024CLIPErase: Efficient Unlearning of Visual-Textual Associations in CLIPcited by 19
  9. 2025RULE: Reinforcement UnLEarning Achieves Forget-Retain Pareto Optimalitycited by 14
  10. 2025Precise In-Parameter Concept Erasure in Large Language Modelscited by 11
  11. 2025CRISP: Persistent Concept Unlearning via Sparse Autoencoderscited by 9
  12. 2025Towards Reliable Forgetting: A Survey on Machine Unlearning Verificationcited by 8
37 more
  1. 2024A Survey on Recommendation Unlearning: Fundamentals, Taxonomy, Evaluation, and Open Questionscited by 7
  2. 2025Generative AI for Autonomous Driving: Frontiers and Opportunitiescited by 7
  3. 2025OFFSIDE: Benchmarking Unlearning Misinformation in Multimodal Large Language Modelscited by 7
  4. 2025Towards Benign Memory Forgetting for Selective Multimodal Large Language Model Unlearningcited by 6
  5. 2026Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarkscited by 6
  6. 2025Beyond Single-Value Metrics: Evaluating and Enhancing LLM Unlearning with Cognitive Diagnosiscited by 5
  7. 2025A Survey on Unlearnable Datacited by 5
  8. 2025"Alexa, can you forget me?" Machine Unlearning Benchmark in Spoken Language Understandingcited by 5
  9. 2025ExAnte: A Benchmark for Ex-Ante Inference in Large Language Modelscited by 5
  10. 2025SUV: Scalable Large Language Model Copyright Compliance with Regularized Selective Unlearningcited by 4
  11. 2025Generative Model Unlearning: A Survey through Target Events, Unlearning Operators, and Evaluation Protocolscited by 4
  12. 2026Forget Many, Forget Right: Scalable and Precise Concept Unlearning in Diffusion Modelscited by 4
  13. 2026Reinforcement Unlearning via Group Relative Policy Optimizationcited by 4
  14. 2025Now You See It, Now You Don't - Instant Concept Erasure for Safe Text-to-Image and Video Generationcited by 3
  15. 2025The Erasure Illusion: Stress-Testing the Generalization of LLM Forgetting Evaluationcited by 3
  16. 2025Exploring Incremental Unlearning: Techniques, Challenges, and Future Directionscited by 2
  17. 2025Ready2Unlearn: A Learning-Time Approach for Preparing Models with Future Unlearning Readinesscited by 2
  18. 2025Dual-Space Smoothness for Robust and Balanced LLM Unlearningcited by 2
  19. 2025A Survey on Unlearning in Large Language Modelscited by 2
  20. 2025Realistic Image-to-Image Machine Unlearning via Decoupling and Knowledge Retentioncited by 1
  21. 2025Mitigating Sensitive Information Leakage in LLMs4Code through Machine Unlearningcited by 1
  22. 2025Automating Evaluation of Diffusion Model Unlearning with (Vision-) Language Model World Knowledgecited by 1
  23. 2025Invisible Watermarks, Visible Gains: Steering Machine Unlearning with Bi-Level Watermarking Designcited by 1
  24. 2025No Encore: Unlearning as Opt-Out in Music Generationcited by 1
  25. 2025Beyond Sharp Minima: Robust LLM Unlearning via Feedback-Guided Multi-Point Optimizationcited by 1
  26. 2026Forget-It-All: Multi-Concept Machine Unlearning via Concept-Aware Neuron Maskingcited by 1
  27. 2026Beyond Text Prompts: Precise Concept Erasure through Text-Image Collaborationcited by 1
  28. 2026PPU-Bench:Real World Benchmark for Personalized Partial Unlearning in Vision Language Modelscited by 1
  29. 2026Beyond Binary Rewards: A Comparative Study of Reward Design for Reinforcement Unlearningcited by 1
  30. 2024Targeted Therapy in Data Removal: Object Unlearning Based on Scene Graphscited by 0
  31. 2025Adaptive-lambda Subtracted Importance Sampled Scores in Machine Unlearning for DDPMs and VAEscited by 0
  32. 2026Teaching Large Language Models When Not to Know: Learning Temporal Critique for Ex-Ante Reasoningcited by 0
  33. 2026SafeDiffusion-R1: Online Reward Steering for Safe Diffusion Post-Trainingcited by 0
  34. 2026MLUBench: A Benchmark for Lifelong Unlearning Evaluation in MLLMscited by 0
  35. 2026PPE-Bench: A Benchmark for Evaluating MLLM Unlearning under Private-Public Entanglementcited by 0
  36. 2026Forgotten in Weights, Recovered by Tools: Agentic Tool Unlearning for LLM Agentscited by 0
  37. 2026BLADE: Bilevel Low-rank Augmented-Lagrangian Erasure for LLM Unlearningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Rethinking Machine Unlearning for Large Language Models
  2. 2025UNO: Unlearning via Orthogonalization in Generative models
  3. 2024Boosting Alignment for Post-Unlearning Text-to-Image Generative Models
  4. 2026On the Robustness of Machine Unlearning for Vision-Language Models
  5. 2024Generative AI for Synthetic Data Generation: Methods, Challenges and the Future
  6. 2025LoReUn: Data Itself Implicitly Provides Cues to Improve Machine Unlearning
  7. 2025Prompting Forgetting: Unlearning in GANs via Textual Guidance
  8. 2026PECKER: A Precisely Efficient Critical Knowledge Erasure Recipe For Machine Unlearning in Diffusion Models