mlsanityData to 7 Oct 2026

Exclusive Unlearning

arXiv 2604.06154 ↗First posted 7 Apr 2026cs.CLcited by 0

On the map: LLM safety and security → Machine unlearning

Abstract (arXiv)

When introducing Large Language Models (LLMs) into industrial applications, such as healthcare and education, the risk of generating harmful content becomes a significant challenge. While existing machine unlearning methods can erase specific harmful knowledge and expressions, diverse harmful content makes comprehensive removal difficult. In this study, instead of individually listing targets for forgetting, we propose Exclusive Unlearning (EU), which aims for broad harm removal by extensively forgetting everything except for the knowledge and expressions we wish to retain. We demonstrate that through Exclusive Unlearning, it is possible to obtain a model that ensures safety against a wide range of inputs, including jailbreaks, while maintaining the ability to respond to diverse instructions related to specific domains such as medicine and mathematics.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Machine unlearning, one of 12 directions in LLM safety and security. Builds on 38 of its 44 references that are in the map. First posted on arXiv 7 Apr 2026.

Builds on

38 of 44 references.

Closest ancestors · 10

Same direction, newest first

  1. 2025BLUR: A Benchmark for LLM Unlearning Robust to Forget-Retain Overlap28 May
  2. 2025Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond7 Feb
  3. 2024A Closer Look at Machine Unlearning for Large Language Models10 Oct
  4. 2024An Adversarial Perspective on Machine Unlearning for AI Safety26 Sep
  5. 2024Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearning19 Jun
  6. 2024Avoiding Copyright Infringement via Large Language Model Unlearning16 Jun
  7. 2024Large Scale Knowledge Washing26 May
  8. 2024Machine Unlearning of Pre-trained Large Language Models23 Feb
  9. 2024Towards Safer Large Language Models through Machine Unlearning15 Feb
  10. 2024Rethinking Machine Unlearning for Large Language Models13 Feb

Other references · 28

  1. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  2. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  3. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  4. 2019HellaSwag: Can a Machine Really Finish Your Sentence?cited by 4,018
  5. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 2,914
  6. 2019PIQA: Reasoning about Physical Commonsense in Natural Languagecited by 2,818
  7. 2023Jailbroken: How Does LLM Safety Training Fail?cited by 1,565
  8. 2020What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Examscited by 1,324
  9. 2019PubMedQA: A Dataset for Biomedical Research Question Answeringcited by 1,271
  10. 2022Quantifying Memorization Across Neural Language Modelscited by 755
  11. 2023AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Modelscited by 738
  12. 2023MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Modelscited by 724
16 more
  1. 2019MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalismscited by 653
  2. 2022MedMCQA : A Large-scale Multi-Subject Multi-Choice Dataset for Medical domain Question Answeringcited by 525
  3. 2023GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Promptscited by 520
  4. 2023Jailbreaking ChatGPT via Prompt Engineering: An Empirical Studycited by 478
  5. 2023ChatDoctor: A Medical Chat Model Fine-Tuned on a Large Language Model Meta-AI (LLaMA) Using Medical Domain Knowledgecited by 324
  6. 2023Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attackscited by 268
  7. 2024PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preferencecited by 252
  8. 2022Are Large Pre-Trained Language Models Leaking Your Personal Information?cited by 195
  9. 2019HEAD-QA: A Healthcare Dataset for Complex Reasoningcited by 100
  10. 2022Preventing Verbatim Memorization in Language Models Gives a False Sense of Privacycited by 97
  11. 2023AlpaCare:Instruction-tuned Large Language Models for Medical Applicationcited by 88
  12. 2018A Systematic Classification of Knowledge, Reasoning, and Context within the ARC Datasetcited by 54
  13. 2024ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectorscited by 48
  14. 2024Eraser: Jailbreaking Defense in Large Language Models via Unlearning Harmful Knowledgecited by 48
  15. 2024From Theft to Bomb-Making: The Ripple Effect of Unlearning in Defending Against Jailbreak Attackscited by 29
  16. 2025SafeLLM: Unlearning Harmful Outputs from Large Language Models against Jailbreak Attackscited by 4

Built on by

Not cited yet.