# UnUnlearning: Unlearning is not sufficient for content regulation in advanced generative AI

arXiv: https://arxiv.org/abs/2407.00106 · HTML: https://mlsanity.com/paper/2407.00106/

## Key facts

- Cited by 51 papers in the map (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 17 of its 23 references that are in the map.
- First posted on arXiv 27 Jun 2024.

## Placed in

- LLM safety and security / [Machine unlearning](https://mlsanity.com/safety/machine-unlearning/)

## Builds on (most cited first, 17 of 17)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks](https://mlsanity.com/paper/1911.04933/) (2019)
- [Making AI Forget You: Data Deletion in Machine Learning](https://mlsanity.com/paper/1907.05012/) (2019)
- [SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation](https://mlsanity.com/paper/2310.12508/) (2023)
- [Remember What You Want to Forget: Algorithms for Machine Unlearning](https://mlsanity.com/paper/2103.03279/) (2021)
- [Large Language Model Unlearning](https://mlsanity.com/paper/2310.10683/) (2023)
- [Forget-Me-Not: Learning to Forget in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.17591/) (2023)
- [Towards Unbounded Machine Unlearning](https://mlsanity.com/paper/2302.09880/) (2023)
- [On the Necessity of Auditable Algorithmic Definitions for Machine Unlearning](https://mlsanity.com/paper/2110.11891/) (2021)
- [Eight Methods to Evaluate Robust Unlearning in LLMs](https://mlsanity.com/paper/2402.16835/) (2024)
- [Towards Safer Large Language Models through Machine Unlearning](https://mlsanity.com/paper/2402.10058/) (2024)
- [Backdoor Defense with Machine Unlearning](https://mlsanity.com/paper/2201.09538/) (2022)
- [Self-Destructing Models: Increasing the Costs of Harmful Dual Uses of Foundation Models](https://mlsanity.com/paper/2211.14946/) (2022)
- [In-Context Learning Learns Label Relationships but Is Not Conventional Learning](https://mlsanity.com/paper/2307.12375/) (2023)
- [In-Context Learning for Text Classification with Many Labels](https://mlsanity.com/paper/2309.10954/) (2023)
- [Fast Exact Unlearning for In-Context Learning Data for LLMs](https://mlsanity.com/paper/2402.00751/) (2024)

## Built on by (most cited first, 30 of 51)

- [MUSE: Machine Unlearning Six-Way Evaluation for Language Models](https://mlsanity.com/paper/2407.06460/) (2024)
- [An Adversarial Perspective on Machine Unlearning for AI Safety](https://mlsanity.com/paper/2409.18025/) (2024)
- [Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond](https://mlsanity.com/paper/2502.05374/) (2025)
- [Protecting Privacy in Multimodal Large Language Models with MLLMU-Bench](https://mlsanity.com/paper/2410.22108/) (2024)
- [On Evaluating the Durability of Safeguards for Open-Weight LLMs](https://mlsanity.com/paper/2412.07097/) (2024)
- [LLM Unlearning via Neural Activation Redirection](https://mlsanity.com/paper/2502.07218/) (2025)
- [Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Concepts](https://mlsanity.com/paper/2410.12777/) (2024)
- [Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities](https://mlsanity.com/paper/2502.05209/) (2025)
- [A Survey on Data Contamination for Large Language Models](https://mlsanity.com/paper/2502.14425/) (2025)
- [Representation Bending for Large Language Model Safety](https://mlsanity.com/paper/2504.01550/) (2025)
- [Towards Robust Knowledge Unlearning: An Adversarial Framework for Assessing and Improving Unlearning Robustness in Large Language Models](https://mlsanity.com/paper/2408.10682/) (2024)
- [When Machine Unlearning Meets Retrieval-Augmented Generation (RAG): Keep Secret or Forget Knowledge?](https://mlsanity.com/paper/2410.15267/) (2024)
- [BLUR: A Bi-Level Optimization Approach for LLM Unlearning](https://mlsanity.com/paper/2506.08164/) (2025)
- [Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy](https://mlsanity.com/paper/2410.09591/) (2024)
- [Knowledge Updating? No More Model Editing! Just Selective Contextual Reasoning](https://mlsanity.com/paper/2503.05212/) (2025)
- [Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Research](https://mlsanity.com/paper/2412.06966/) (2024)
- [Position: Adversarial ML for LLMs Is Not Making Any Progress](https://mlsanity.com/paper/2502.02260/) (2025)
- [Mitigating Memorization In Language Models](https://mlsanity.com/paper/2410.02159/) (2024)
- [From Dormant to Deleted: Tamper-Resistant Unlearning Through Weight-Space Regularization](https://mlsanity.com/paper/2505.22310/) (2025)
- [CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-Tuning](https://mlsanity.com/paper/2505.16559/) (2025)
- [Beyond Data Filtering: Knowledge Localization for Capability Removal in LLMs](https://mlsanity.com/paper/2512.05648/) (2025)
- [UIPE: Enhancing LLM Unlearning by Removing Knowledge Related to Forgetting Targets](https://mlsanity.com/paper/2503.04693/) (2025)
- [Improving LLM Unlearning Robustness via Random Perturbations](https://mlsanity.com/paper/2501.19202/) (2025)
- [Rectifying Privacy and Efficacy Measurements in Machine Unlearning: A New Inference Attack Perspective](https://mlsanity.com/paper/2506.13009/) (2025)
- [Position: Bridge the Gaps between Machine Unlearning and AI Regulation](https://mlsanity.com/paper/2502.12430/) (2025)
- [Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods](https://mlsanity.com/paper/2506.10236/) (2025)
- [Reference-Specific Unlearning Metrics Can Hide the Truth: A Reality Check](https://mlsanity.com/paper/2510.12981/) (2025)
- [SUA: Stealthy Multimodal Large Language Model Unlearning Attack](https://mlsanity.com/paper/2506.17265/) (2025)
- [Generative Model Unlearning: A Survey through Target Events, Unlearning Operators, and Evaluation Protocols](https://mlsanity.com/paper/2507.19894/) (2025)
- [Reliable Unlearning Harmful Information in LLMs with Metamorphosis Representation Projection](https://mlsanity.com/paper/2508.15449/) (2025)

## Abstract (arXiv)

Exact unlearning was first introduced as a privacy mechanism that allowed a user to retract their data from machine learning models on request. Shortly after, inexact schemes were proposed to mitigate the impractical costs associated with exact unlearning. More recently unlearning is often discussed as an approach for removal of impermissible knowledge i.e. knowledge that the model should not possess such as unlicensed copyrighted, inaccurate, or malicious information. The promise is that if the model does not have a certain malicious capability, then it cannot be used for the associated malicious purpose. In this paper we revisit the paradigm in which unlearning is used for in Large Language Models (LLMs) and highlight an underlying inconsistency arising from in-context learning. Unlearning can be an effective control mechanism for the training phase, yet it does not prevent the model from performing an impermissible act during inference. We introduce a concept of ununlearning, where unlearned knowledge gets reintroduced in-context, effectively rendering the model capable of behaving as if it knows the forgotten knowledge. As a result, we argue that content filtering for impermissible knowledge will be required and even exact unlearning schemes are not enough for effective content regulation. We discuss feasibility of ununlearning for modern LLMs and examine broader implications.