mlsanityData to 14 Oct 2026

CURaTE: Continual Unlearning in Real Time with Ensured Preservation of LLM Knowledge

arXiv 2604.14644 ↗First posted 16 Apr 2026cs.CL cs.LGcited by 0

On the map: LLM safety and security → Machine unlearning

Abstract (arXiv)

The inability to filter out in advance all potentially problematic data from the pre-training of large language models has given rise to the need for methods for unlearning specific pieces of knowledge after training. Existing techniques overlook the need for continuous and immediate action, causing them to suffer from degraded utility as updates accumulate and protracted exposure of sensitive information. To address these issues, we propose Continual Unlearning in Real Time with Ensured Preservation of LLM Knowledge (CURaTE). Our method begins by training a sentence embedding model on a dataset designed to enable the formation of sharp decision boundaries for determining whether a given input prompt corresponds to any stored forget requests. The similarity of a given input to the forget requests is then used to determine whether to answer or return a refusal response. We show that even with such a simple approach, not only does CURaTE achieve more effective forgetting than existing methods, but by avoiding modification of the language model parameters, it also maintains near perfect knowledge preservation over any number of updates and is the only method capable of continual unlearning in real-time.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Machine unlearning, one of 12 directions in LLM safety and security. Builds on 26 of its 31 references that are in the map. First posted on arXiv 16 Apr 2026.

Builds on

26 of 31 references.

Closest ancestors · 9

Same direction, newest first

  1. 2025GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection19 May
  2. 2024On Large Language Model Continual Unlearning14 Jul
  3. 2024Learning to Refuse: Towards Mitigating Privacy Risks in LLMs14 Jul
  4. 2024SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning28 Apr
  5. 2024Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning8 Apr
  6. 2024TOFU: A Task of Fictitious Unlearning for LLMs11 Jan
  7. 2023In-Context Unlearning: Language Models as Few Shot Unlearners11 Oct
  8. 2022Knowledge Unlearning for Mitigating Privacy Risks in Language Models4 Oct
  9. 2022Continual Learning and Private Unlearning24 Mar

Other references · 17

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  4. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,307
  5. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
  6. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  7. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,975
  8. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  9. 2022Locating and Editing Factual Associations in GPTcited by 2,691
  10. 2018Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answeringcited by 2,164
  11. 2022Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answeringcited by 1,919
  12. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,822
5 more
  1. 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,073
  2. 2020MPNet: Masked and Permuted Pre-training for Language Understandingcited by 981
  3. 2023An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuningcited by 639
  4. 2024AlphaEdit: Null-Space Constrained Knowledge Editing for Language Modelscited by 236
  5. 2019WinoGrande: An Adversarial Winograd Schema Challenge at Scalecited by 204

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Unlearning That Lasts: Utility-Preserving, Robust, and Almost Irreversible Forgetting in LLMs
  2. 2026FIT to Forget: Robust Continual Unlearning for Large Language Models
  3. 2025BLUR: A Benchmark for LLM Unlearning Robust to Forget-Retain Overlap
  4. 2025Forget to Know, Remember to Use: Context-Aware Unlearning for Large Language Models
  5. 2026Attention Smoothing Is All You Need For Unlearning
  6. 2026ICCU: In-Context Continual Unlearning via Pattern-Induced Refusal Rules
  7. 2026Not Every Change Is Necessary: Recoverable Drift in Large Language Model Unlearning
  8. 2026Unlearning in LLMs: Methods, Evaluation, and Open Challenges