mlsanityData to 7 Oct 2026

Privacy Adhering Machine Un-learning in NLP

arXiv 2212.09573 ↗First posted 19 Dec 2022cs.CLcited by 35

On the map: LLM safety and security → Machine unlearning

Abstract (arXiv)

Regulations introduced by General Data Protection Regulation (GDPR) in the EU or California Consumer Privacy Act (CCPA) in the US have included provisions on the textitright to be forgotten that mandates industry applications to remove data related to an individual from their systems. In several real world industry applications that use Machine Learning to build models on user data, such mandates require significant effort both in terms of data cleansing as well as model retraining while ensuring the models do not deteriorate in prediction quality due to removal of data. As a result, continuous removal of data and model retraining steps do not scale if these applications receive such requests at a very high frequency. Recently, a few researchers proposed the idea of textitMachine Unlearning to tackle this challenge. Despite the significant importance of this task, the area of Machine Unlearning is under-explored in Natural Language Processing (NLP) tasks. In this paper, we explore the Unlearning framework on various GLUE tasks citeWang:18, such as, QQP, SST and MNLI. We propose computationally efficient approaches (SISA-FC and SISA-A) to perform textitguaranteed Unlearning that provides significant reduction in terms of both memory (90-95%), time (100x) and space consumption (99%) in comparison to the baselines while keeping model performance constant.

Key facts. Cited by 35 papers in the map (data through 7 Oct 2026). Placed in Machine unlearning, one of 12 directions in LLM safety and security. Builds on 15 of its 21 references that are in the map. First posted on arXiv 19 Dec 2022.

Builds on

15 of 21 references.

Closest ancestors · 3

Same direction, newest first

  1. 2022Knowledge Unlearning for Mitigating Privacy Risks in Language Models4 Oct
  2. 2022A Survey of Machine Unlearning6 Sep
  3. 2022Deep Unlearning via Randomized Conditionally Independent Hessians15 Apr

Other references · 12

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,854
  4. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  5. 2016Deep Learning with Differential Privacycited by 2,682
  6. 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,665
  7. 2019Machine Unlearningcited by 1,020
  8. 2019Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networkscited by 599
  9. 2021Large Language Models Can Be Strong Differentially Private Learnerscited by 405
  10. 2021Differentially Private Fine-tuning of Language Modelscited by 392
  11. 2020Variational Bayesian Unlearningcited by 114
  12. 2020Machine Unlearning: Linear Filtration for Logit-based Classifierscited by 89

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 5; 2024: 18; 2025: 10; 2026: 2.

35 papers.

Sort:

By area:

  1. 2024Rethinking Machine Unlearning for Large Language Modelscited by 247
  2. 2023Unlearn What You Want to Forget: Efficient Unlearning for LLMscited by 211
  3. 2024Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearningcited by 160
  4. 2024Eight Methods to Evaluate Robust Unlearning in LLMscited by 153
  5. 2024Machine Unlearning of Pre-trained Large Language Modelscited by 118
  6. 2024Large Language Model Unlearning via Embedding-Corrupted Promptscited by 112
  7. 2024Machine Unlearning in Generative AI: A Surveycited by 49
  8. 2023Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomycited by 44
  9. 2024Digital Forgetting in Large Language Models: A Survey of Unlearning Methodscited by 38
  10. 2024LLM-PBE: Assessing Data Privacy in Large Language Modelscited by 38
  11. 2024Offset Unlearning for Large Language Modelscited by 33
  12. 2024PrE-Text: Training Language Models on Private Federated Data in the Age of LLMscited by 29
23 more
  1. 2023SAFE: Machine Unlearning With Shard Graphscited by 28
  2. 2024Towards Scalable Exact Machine Unlearning Using Parameter-Efficient Fine-Tuningcited by 25
  3. 2024Unified Parameter-Efficient Unlearning for LLMscited by 24
  4. 2024Ethos: Rectifying Language Models in Orthogonal Parameter Spacecited by 20
  5. 2023Training Data Protection with Compositional Diffusion Modelscited by 16
  6. 2024SEUF: Is Unlearning One Expert Enough for Mixture-of-Experts LLMs?cited by 14
  7. 2024Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Researchcited by 14
  8. 2025Do LLMs Really Forget? Evaluating Unlearning with Knowledge Correlation and Confidence Awarenesscited by 13
  9. 2025SALAD: Systematic Assessment of Machine Unlearning on LLM-Aided Hardware Designcited by 10
  10. 2023AI Model Disgorgement: Methods and Choicescited by 9
  11. 2025UCD: Unlearning in LLMs via Contrastive Decodingcited by 9
  12. 2025Towards Reliable Forgetting: A Survey on Machine Unlearning Verificationcited by 8
  13. 2024Learn while Unlearn: An Iterative Unlearning Framework for Generative Language Modelscited by 5
  14. 2024Strong Copyright Protection for Language Models via Adaptive Model Fusioncited by 4
  15. 2025Deep Contrastive Unlearning for Language Modelscited by 4
  16. 2025Neural Breadcrumbs: Membership Inference Attacks on LLMs Through Hidden State and Attention Pattern Analysiscited by 3
  17. 2024RESTOR: Knowledge Recovery in Machine Unlearningcited by 2
  18. 2025Efficient Verified Machine Unlearning For Distillationcited by 2
  19. 2025Towards Evaluation for Real-World LLM Unlearningcited by 2
  20. 2025A Survey on Unlearning in Large Language Modelscited by 2
  21. 2026Inference-time Unlearning Using Conformal Predictioncited by 2
  22. 2025Layered Unlearning for Adversarial Relearningcited by 1
  23. 2026PrivBench: A Holistic and Modular Benchmarking Platform for Evaluating Text-to-Text Privatizationcited by 0