mlsanityData to 7 Oct 2026

Knowledge Sanitization of Large Language Models

arXiv 2309.11852 ↗First posted 21 Sep 2023cs.CLcited by 34

Not on the map. Why?

Cited by 24 in LLM safety and security, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We explore a knowledge sanitization approach to mitigate the privacy concerns associated with large language models (LLMs). LLMs trained on a large corpus of Web data can memorize and potentially reveal sensitive or confidential information, raising critical security concerns. Our technique efficiently fine-tunes these models using the Low-Rank Adaptation (LoRA) method, prompting them to generate harmless responses such as ``I don't know'' when queried about specific information. Experimental results in a closed-book question-answering task show that our straightforward method not only minimizes particular knowledge leakage but also preserves the overall performance of LLMs. These two advantages strengthen the defense against extraction attacks and reduces the emission of harmful content such as hallucinations.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). Builds on 29 of its 38 references that are in the map. First posted on arXiv 21 Sep 2023.

Builds on

29 of 38 references.

References · 29

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2023GPT-4 Technical Reportcited by 18,132
  4. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  5. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  6. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  7. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  8. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,710
  9. 2019HellaSwag: Can a Machine Really Finish Your Sentence?cited by 4,018
  10. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 2,914
  11. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  12. 2016Deep Learning with Differential Privacycited by 2,682
17 more
  1. 2022Locating and Editing Factual Associations in GPTcited by 2,609
  2. 2020Extracting Training Data from Large Language Modelscited by 2,144
  3. 2019BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questionscited by 2,140
  4. 2018Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answeringcited by 2,114
  5. 2020Transformer Feed-Forward Layers Are Key-Value Memoriescited by 1,307
  6. 2022LaMDA: Language Models for Dialog Applicationscited by 1,218
  7. 2022Editing Models with Task Arithmeticcited by 1,076
  8. 2017RACE: Large-scale ReAding Comprehension Dataset From Examinationscited by 851
  9. 2022Quantifying Memorization Across Neural Language Modelscited by 755
  10. 2022GPT-NeoX-20B: An Open-Source Autoregressive Language Modelcited by 711
  11. 2019Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networkscited by 599
  12. 2021Knowledge Neurons in Pretrained Transformerscited by 590
  13. 2022Knowledge Unlearning for Mitigating Privacy Risks in Language Modelscited by 424
  14. 2020ToTTo: A Controlled Table-To-Text Generation Datasetcited by 267
  15. 2022Are Large Pre-Trained Language Models Leaking Your Personal Information?cited by 195
  16. 2020Formalizing Data Deletion in the Context of the Right to be Forgottencited by 46
  17. 2014C-sanitized: a privacy model for document redaction and sanitizationcited by 27

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 14; 2025: 15; 2026: 4.

34 papers.

Sort:

By area:

  1. 2024Rethinking Machine Unlearning for Large Language Modelscited by 247
  2. 2024Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearningcited by 160
  3. 2024Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMscited by 158
  4. 2024A Comprehensive Study of Knowledge Editing for Large Language Modelscited by 157
  5. 2024Eight Methods to Evaluate Robust Unlearning in LLMscited by 153
  6. 2024RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Modelscited by 77
  7. 2024A Closer Look at Machine Unlearning for Large Language Modelscited by 54
  8. 2025LLM Unlearning via Neural Activation Redirectioncited by 38
  9. 2023Identifying and Mitigating Privacy Risks Stemming from Language Models: A Surveycited by 30
  10. 2024Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Surveycited by 23
  11. 2024UnStar: Unlearning with Self-Taught Anti-Sample Reasoning for LLMscited by 14
  12. 2024Lifelong Knowledge Editing for Vision Language Models with Low-Rank Mixture-of-Expertscited by 14
22 more
  1. 2025SoK: Machine Unlearning for Large Language Modelscited by 9
  2. 2025UCD: Unlearning in LLMs via Contrastive Decodingcited by 9
  3. 2025Unlearning That Lasts: Utility-Preserving, Robust, and Almost Irreversible Forgetting in LLMscited by 9
  4. 2025CLUE: Conflict-guided Localization for LLM Unlearning Frameworkcited by 7
  5. 2026Attention Smoothing Is All You Need For Unlearningcited by 6
  6. 2024Recent Advances in Attack and Defense Approaches of Large Language Modelscited by 5
  7. 2024SoK: Prompt Hacking of Large Language Modelscited by 5
  8. 2025Distribution Preference Optimization: A Fine-grained Perspective for LLM Unlearningcited by 3
  9. 2024RESTOR: Knowledge Recovery in Machine Unlearningcited by 2
  10. 2024The Future of Intelligent Healthcare: A Systematic Analysis and Discussion on the Integration and Impact of Robots Using Large Language Models for Healthcarecited by 2
  11. 2025Helping Large Language Models Protect Themselves: An Enhanced Filtering and Summarization Systemcited by 2
  12. 2025Align-then-Unlearn: Embedding Alignment for LLM Unlearningcited by 2
  13. 2025Towards Evaluation for Real-World LLM Unlearningcited by 2
  14. 2025Towards Safer Chatbots: Automated Policy Compliance Evaluation of Custom GPTscited by 1
  15. 2025MIAT: Maneuver-Intention-Aware Transformer for Spatio-Temporal Trajectory Predictioncited by 1
  16. 2025Layered Unlearning for Adversarial Relearningcited by 1
  17. 2025Learning-Time Encoding Shapes Unlearning in LLMscited by 1
  18. 2025Forgetting-MarI: LLM Unlearning via Marginal Information Regularizationcited by 1
  19. 2026DurableUn: Quantization-Induced Recovery Attacks in Machine Unlearningcited by 1
  20. 2025Lifting Data-Tracing Machine Unlearning to Knowledge-Tracing for Foundation Modelscited by 0
  21. 2026Shadow Unlearning: A Neuro-Semantic Approach to Fidelity-Preserving Faceless Forgetting in LLMscited by 0
  22. 2026Towards Localized and Disentangled Knowledge Editing for Multimodal Large Language Modelscited by 0