mlsanityData to 7 Oct 2026

Enhancing Data Privacy in Large Language Models through Private Association Editing

arXiv 2406.18221 ↗First posted 26 Jun 2024cs.CL cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

Large language models (LLMs) require a significant redesign in solutions to preserve privacy in data-intensive applications due to their text-generation capabilities. Indeed, LLMs tend to memorize and emit private information when maliciously prompted. In this paper, we introduce Private Association Editing (PAE) as a novel defense approach for private data leakage. PAE is designed to effectively remove Personally Identifiable Information (PII) without retraining the model. Experimental results demonstrate the effectiveness of PAE with respect to alternative baseline methods. We believe PAE will serve as a critical tool in the ongoing effort to protect data privacy in LLMs, encouraging the development of safer models for real-world applications.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 31 of its 48 references that are in the map. First posted on arXiv 26 Jun 2024.

Builds on

31 of 48 references.

References · 31

  1. 2022Locating and Editing Factual Associations in GPTcited by 2,609
  2. 2020The Pile: An 800GB Dataset of Diverse Text for Language Modelingcited by 2,346
  3. 2020Extracting Training Data from Large Language Modelscited by 2,144
  4. 2019Language Models as Knowledge Bases?cited by 1,922
  5. 2023Pythia: A Suite for Analyzing Large Language Models Across Training and Scalingcited by 1,734
  6. 2020Transformer Feed-Forward Layers Are Key-Value Memoriescited by 1,307
  7. 2021Scaling Language Models: Methods, Analysis & Insights from Training Gophercited by 1,199
  8. 2022Mass-Editing Memory in a Transformercited by 976
  9. 2016The LAMBADA dataset: Word prediction requiring a broad discourse contextcited by 960
  10. 2018The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networkscited by 847
  11. 2022GPT-NeoX-20B: An Open-Source Autoregressive Language Modelcited by 711
  12. 2021Editing Factual Knowledge in Language Modelscited by 548
19 more
  1. 2023DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Modelscited by 505
  2. 2022Memory-Based Model Editing at Scalecited by 443
  3. 2023Scalable Extraction of Training Data from (Production) Language Modelscited by 415
  4. 2023Editing Large Language Models: Problems, Methods, and Opportunitiescited by 367
  5. 2023Large Language Models are Zero-Shot Rankers for Recommender Systemscited by 307
  6. 2024Rethinking Machine Unlearning for Large Language Modelscited by 247
  7. 2022Are Large Pre-Trained Language Models Leaking Your Personal Information?cited by 195
  8. 2022What Does it Mean for a Language Model to Preserve Privacy?cited by 194
  9. 2023Knowledge Editing for Large Language Models: A Surveycited by 189
  10. 2020How Context Affects Language Models' Factual Predictionscited by 181
  11. 2023Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attackscited by 156
  12. 2021Counterfactual Memorization in Neural Language Modelscited by 155
  13. 2024Model Editing at Scale leads to Gradual and Catastrophic Forgettingcited by 92
  14. 2024The Butterfly Effect of Model Editing: Few Edits Can Trigger Large Language Models Collapsecited by 54
  15. 2024Rebuilding ROME : Resolving Model Collapse during Sequential Model Editingcited by 50
  16. 2023Controlling the Extraction of Memorized Data from Large Language Models via Prompt-Tuningcited by 40
  17. 2024WilKE: Wise-Layer Knowledge Editor for Lifelong Knowledge Editingcited by 40
  18. 2023Augmenting Large Language Model Translators via Translation Memoriescited by 21
  19. 2022The Dark Side of the Language: Pre-trained Transformers in the DarkNetcited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 2; 2026: 1.

4 papers.

  1. 2024To Forget or Not? Towards Practical Knowledge Unlearning for Large Language Modelscited by 25
  2. 2025Position: Editing Large Language Models Poses Serious Safety Riskscited by 15
  3. 2025Large Language Model Sourcing: A Surveycited by 5
  4. 2026Do LLMs Really Memorize Personally Identifiable Information? Revisiting PII Leakage with a Cue-Controlled Memorization Frameworkcited by 3