# Textual Unlearning Gives a False Sense of Unlearning

arXiv: https://arxiv.org/abs/2406.13348 · HTML: https://mlsanity.com/paper/2406.13348/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 21 of its 34 references that are in the map.
- First posted on arXiv 19 Jun 2024.

## Placed in

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

## Builds on (most cited first, 21 of 21)

- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling](https://mlsanity.com/paper/2304.01373/) (2023)
- [Editing Models with Task Arithmetic](https://mlsanity.com/paper/2212.04089/) (2022)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Membership Inference Attacks From First Principles](https://mlsanity.com/paper/2112.03570/) (2021)
- [TOFU: A Task of Fictitious Unlearning for LLMs](https://mlsanity.com/paper/2401.06121/) (2024)
- [Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning](https://mlsanity.com/paper/2404.05868/) (2024)
- [Knowledge Unlearning for Mitigating Privacy Risks in Language Models](https://mlsanity.com/paper/2210.01504/) (2022)
- [Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment](https://mlsanity.com/paper/2308.05374/) (2023)
- [Membership Inference Attacks against Language Models via Neighbourhood Comparison](https://mlsanity.com/paper/2305.18462/) (2023)
- [In-Context Unlearning: Language Models as Few Shot Unlearners](https://mlsanity.com/paper/2310.07579/) (2023)
- [Unlearn What You Want to Forget: Efficient Unlearning for LLMs](https://mlsanity.com/paper/2310.20150/) (2023)
- [When Machine Unlearning Jeopardizes Privacy](https://mlsanity.com/paper/2005.02205/) (2020)
- [Do Membership Inference Attacks Work on Large Language Models?](https://mlsanity.com/paper/2402.07841/) (2024)
- [Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of Privacy](https://mlsanity.com/paper/2403.01218/) (2024)
- [LAMP: Extracting Text from Gradients with Language Model Priors](https://mlsanity.com/paper/2202.08827/) (2022)
- [Learn What You Want to Unlearn: Unlearning Inversion Attacks against Machine Unlearning](https://mlsanity.com/paper/2404.03233/) (2024)
- [Evaluations of Machine Learning Privacy Defenses are Misleading](https://mlsanity.com/paper/2404.17399/) (2024)
- [A Synthetic Dataset for Personal Attribute Inference](https://mlsanity.com/paper/2406.07217/) (2024)

## Built on by (most cited first, 13 of 13)

- [SoK: Machine Unlearning for Large Language Models](https://mlsanity.com/paper/2506.09227/) (2025)
- [Matter-of-Fact: A Benchmark for Verifying the Feasibility of Literature-Supported Claims in Materials Science](https://mlsanity.com/paper/2506.04410/) (2025)
- [Attention Smoothing Is All You Need For Unlearning](https://mlsanity.com/paper/2603.01285/) (2026)
- [Erasing Without Remembering: Implicit Knowledge Forgetting in Large Language Models](https://mlsanity.com/paper/2502.19982/) (2025)
- [A Survey on Unlearning in Large Language Models](https://mlsanity.com/paper/2510.25117/) (2025)
- [Towards Benchmarking Privacy Vulnerabilities in Selective Forgetting with Large Language Models](https://mlsanity.com/paper/2512.18035/) (2025)
- [Multilingual Unlearning in LLMs: Transfer, Dynamics, and Reversibility](https://mlsanity.com/paper/2606.03291/) (2026)
- [Unlearning at Scale: State-Exact Trace-Preserving Deletion in Billion-Parameter Language Models](https://mlsanity.com/paper/2508.12220/) (2025)
- [Retain-Neutral Surrogates for Min-Max Unlearning](https://mlsanity.com/paper/2605.05871/) (2026)
- [SPACE: Source-free Proxy Anchor Concept Erasure for MLLMs](https://mlsanity.com/paper/2606.09868/) (2026)
- [The Privacy-Hallucination Tradeoff in Differentially Private Language Models](https://mlsanity.com/paper/2609.00492/) (2026)
- [Damnatio Memoriae: Adversarially and Selectively Forgetting Identities in the Embedding Space of Face Recognition Models](https://mlsanity.com/paper/2609.27115/) (2026)
- [The Tokens Remember: When Tokenization Bypasses Knowledge Editing and Unlearning](https://mlsanity.com/paper/2609.29045/) (2026)

## Abstract (arXiv)

Language Models (LMs) are prone to ''memorizing'' training data, including substantial sensitive user information. To mitigate privacy risks and safeguard the right to be forgotten, machine unlearning has emerged as a promising approach for enabling LMs to efficiently ''forget'' specific texts. However, despite the good intentions, is textual unlearning really as effective and reliable as expected? To address the concern, we first propose Unlearning Likelihood Ratio Attack+ (U-LiRA+), a rigorous textual unlearning auditing method, and find that unlearned texts can still be detected with very high confidence after unlearning. Further, we conduct an in-depth investigation on the privacy risks of textual unlearning mechanisms in deployment and present the Textual Unlearning Leakage Attack (TULA), along with its variants in both black- and white-box scenarios. We show that textual unlearning mechanisms could instead reveal more about the unlearned texts, exposing them to significant membership inference and data reconstruction risks. Our findings highlight that existing textual unlearning actually gives a false sense of unlearning, underscoring the need for more robust and secure unlearning mechanisms.