mlsanityData to 13 Oct 2026

Right to be Forgotten in the Era of Large Language Models: Implications, Challenges, and Solutions

arXiv 2307.03941 ↗First posted 8 Jul 2023cs.CY cs.AI cs.CLcited by 60

On the map: LLM safety and security → Machine unlearning

Abstract (arXiv)

The Right to be Forgotten (RTBF) was first established as the result of the ruling of Google Spain SL, Google Inc. v AEPD, Mario Costeja Gonz'alez, and was later included as the Right to Erasure under the General Data Protection Regulation (GDPR) of European Union to allow individuals the right to request personal data be deleted by organizations. Specifically for search engines, individuals can send requests to organizations to exclude their information from the query results. It was a significant emergent right as the result of the evolution of technology. With the recent development of Large Language Models (LLMs) and their use in chatbots, LLM-enabled software systems have become popular. But they are not excluded from the RTBF. Compared with the indexing approach used by search engines, LLMs store, and process information in a completely different way. This poses new challenges for compliance with the RTBF. In this paper, we explore these challenges and provide our insights on how to implement technical solutions for the RTBF, including the use of differential privacy, machine unlearning, model editing, and guardrails. With the rapid advancement of AI and the increasing need of regulating this powerful technology, learning from the case of RTBF can provide valuable lessons for technical practitioners, legal experts, organizations, and authorities.

Key facts. Cited by 60 papers in the map (data through 13 Oct 2026). Placed in Machine unlearning, one of 12 directions in LLM safety and security. Builds on 22 of its 45 references that are in the map. First posted on arXiv 8 Jul 2023.

Builds on

22 of 45 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023To Be Forgotten or To Be Fair: Unveiling Fairness Implications of Machine Unlearning Methods7 Feb

Other references · 21

  1. 2020Language Models are Few-Shot Learnerscited by 32,320
  2. 2023GPT-4 Technical Reportcited by 18,278
  3. 2022Training language models to follow instructions with human feedbackcited by 15,856
  4. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,317
  5. 2023A Survey of Large Language Modelscited by 2,559
  6. 2022Emergent Abilities of Large Language Modelscited by 2,499
  7. 2020Extracting Training Data from Large Language Modelscited by 2,181
  8. 2019Machine Unlearningcited by 1,056
  9. 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 898
  10. 2023Extracting Training Data from Diffusion Modelscited by 729
  11. 2019Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networkscited by 617
  12. 2019Certified Data Removal from Machine Learning Modelscited by 532
9 more
  1. 2021Fast Model Editing at Scalecited by 493
  2. 2022Memory-Based Model Editing at Scalecited by 446
  3. 2020Amnesiac Machine Learningcited by 319
  4. 2023Evaluating Verifiability in Generative Search Enginescited by 299
  5. 2019BERT has a Mouth, and It Must Speak: BERT as a Markov Random Field Language Modelcited by 185
  6. 2022Synthetic Text Generation with Differential Privacy: A Simple and Practical Recipecited by 108
  7. 2018Privacy Preserving Machine Learning: Threats and Solutionscited by 79
  8. 2018Learning Semantic Textual Similarity from Conversationscited by 41
  9. 2019Pre-trained Language Model Representations for Language Generationcited by 34

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2023: 7; 2024: 24; 2025: 20; 2026: 9.

60 papers.

Sort:

By area:

  1. 2024TOFU: A Task of Fictitious Unlearning for LLMscited by 519
  2. 2023Who's Harry Potter? Approximate Unlearning in LLMscited by 376
  3. 2024Rethinking Machine Unlearning for Large Language Modelscited by 254
  4. 2023Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attackscited by 157
  5. 2024Guardrail Baselines for Unlearning in LLMscited by 93
  6. 2023SILO Language Models: Isolating Legal Risk In a Nonparametric Datastorecited by 71
  7. 2024Position: LLM Unlearning Benchmarks are Weak Measures of Progresscited by 62
  8. 2025Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go Beyondcited by 60
  9. 2024A Closer Look at Machine Unlearning for Large Language Modelscited by 55
  10. 2024On Large Language Model Continual Unlearningcited by 52
  11. 2023Knowledge Unlearning for LLMs: Tasks, Methods, and Challengescited by 38
  12. 2024Offset Unlearning for Large Language Modelscited by 35
38 more
  1. 2024Advances and Open Challenges in Federated Foundation Modelscited by 34
  2. 2024Mask-based Membership Inference Attacks for Retrieval-Augmented Generationcited by 29
  3. 2024Benchmarking Vision Language Model Unlearning via Fictitious Facial Identity Datasetcited by 29
  4. 2024Generative AI in EU Law: Liability, Privacy, Intellectual Property, and Cybersecuritycited by 21
  5. 2024Extracting Unlearned Information from LLMs with Activation Steeringcited by 20
  6. 2024Unbridled Icarus: A Survey of the Potential Perils of Image Inputs in Multimodal Large Language Model Securitycited by 19
  7. 2024The Frontier of Data Erasure: Machine Unlearning for Large Language Modelscited by 17
  8. 2024Large Scale Knowledge Washingcited by 16
  9. 2024UnStar: Unlearning with Self-Taught Anti-Sample Reasoning for LLMscited by 15
  10. 2024Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Researchcited by 14
  11. 2023REX: Rapid Exploration and eXploitation for AI Agentscited by 13
  12. 2025GRU: Mitigating the Trade-off between Unlearning and Retention for LLMscited by 12
  13. 2025Unlearning That Lasts: Utility-Preserving, Robust, and Almost Irreversible Forgetting in LLMscited by 10
  14. 2025UPCORE: Utility-Preserving Coreset Selection for Balanced Unlearningcited by 7
  15. 2025Does Machine Unlearning Truly Remove Knowledge?cited by 7
  16. 2026MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agentscited by 7
  17. 2024Recent Advances in Attack and Defense Approaches of Large Language Modelscited by 6
  18. 2024Opportunities and Challenges of Generative-AI in Financecited by 6
  19. 2026Attention Smoothing Is All You Need For Unlearningcited by 6
  20. 2024LLM Surgery: Efficient Knowledge Unlearning and Editing in Large Language Modelscited by 5
  21. 2025Erasing Without Remembering: Implicit Knowledge Forgetting in Large Language Modelscited by 5
  22. 2023Defending Our Privacy With Backdoorscited by 4
  23. 2024Reconstruction of Differentially Private Text Sanitization via Large Language Modelscited by 4
  24. 2025Large Language Model Unlearning for Source Codecited by 4
  25. 2025What Should LLMs Forget? Quantifying Personal Data in LLMs for Right-to-Be-Forgotten Requestscited by 4
  26. 2025Generative Model Unlearning: A Survey through Target Events, Unlearning Operators, and Evaluation Protocolscited by 4
  27. 2025Reliable Unlearning Harmful Information in LLMs with Metamorphosis Representation Projectioncited by 4
  28. 2025Investigating Model Editing for Unlearning in Large Language Modelscited by 4
  29. 2024Learning to Forget using Hypernetworkscited by 3
  30. 2025The Right to AIcited by 3
  31. 2025A Survey on Unlearning in Large Language Modelscited by 3
  32. 2023Justifiable Artificial Intelligence: Engineering Large Language Models for Legal Applicationscited by 2
  33. 2025LLM Unlearning Should Be Form-Independentcited by 2
  34. 2025Memory Power Asymmetry in Human-AI Relationships: Preserving Mutual Forgetting in the Digital Agecited by 2
  35. 2026Inference-time Unlearning Using Conformal Predictioncited by 2
  36. 2024MUC: Machine Unlearning for Contrastive Learning with Black-box Evaluationcited by 1
  37. 2024From Machine Learning to Machine Unlearning: Complying with GDPR's Right to be Forgotten while Maintaining Business Value of Predictive Modelscited by 1
  38. 2025FALCON: Fine-grained Activation Manipulation by Contrastive Orthogonal Unalignment for Large Language Modelcited by 1

50 most cited of 60 All 60 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Technical Report for the Forgotten-by-Design Project: Targeted Obfuscation for Machine Learning
  2. 2022Control, Confidentiality, and the Right to be Forgotten
  3. 2023What can we learn from Data Leakage and Unlearning for Law?
  4. 2024Preserving Privacy in Large Language Models: A Survey on Current Threats and Solutions
  5. 2026Privacy Control in Conversational LLM Platforms: A Walkthrough Study
  6. 2026Redakto - The Incognito Tab for LLMs
  7. 2025SoK: The Privacy Paradox of Large Language Models: Advancements, Privacy Risks, and Mitigation
  8. 2024Machine Unlearning for Traditional Models and Large Language Models: A Short Survey