# To Each (Textual Sequence) Its Own: Improving Memorized-Data Unlearning in Large Language Models

arXiv: https://arxiv.org/abs/2405.03097 · HTML: https://mlsanity.com/paper/2405.03097/

## Key facts

- Cited by 43 papers in the map (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 49 of its 65 references that are in the map.
- First posted on arXiv 6 May 2024.

## Placed in

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

## Builds on (most cited first, 30 of 49)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [PubMedQA: A Dataset for Biomedical Research Question Answering](https://mlsanity.com/paper/1909.06146/) (2019)
- [Editing Models with Task Arithmetic](https://mlsanity.com/paper/2212.04089/) (2022)
- [The LAMBADA dataset: Word prediction requiring a broad discourse context](https://mlsanity.com/paper/1606.06031/) (2016)
- [Membership Inference Attacks From First Principles](https://mlsanity.com/paper/2112.03570/) (2021)
- [Quantifying Memorization Across Neural Language Models](https://mlsanity.com/paper/2202.07646/) (2022)
- [Deduplicating Training Data Makes Language Models Better](https://mlsanity.com/paper/2107.06499/) (2021)
- [MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms](https://mlsanity.com/paper/1905.13319/) (2019)
- [Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks](https://mlsanity.com/paper/1911.04933/) (2019)
- [SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization](https://mlsanity.com/paper/1911.12237/) (2019)
- [TOFU: A Task of Fictitious Unlearning for LLMs](https://mlsanity.com/paper/2401.06121/) (2024)
- [Wizard of Wikipedia: Knowledge-Powered Conversational agents](https://mlsanity.com/paper/1811.01241/) (2018)
- [Does Learning Require Memorization? A Short Tale about a Long Tail](https://mlsanity.com/paper/1906.05271/) (2019)
- [Knowledge Unlearning for Mitigating Privacy Risks in Language Models](https://mlsanity.com/paper/2210.01504/) (2022)
- [Large Language Models Can Be Strong Differentially Private Learners](https://mlsanity.com/paper/2110.05679/) (2021)
- [Differentially Private Fine-tuning of Language Models](https://mlsanity.com/paper/2110.06500/) (2021)
- [Amnesiac Machine Learning](https://mlsanity.com/paper/2010.10981/) (2020)
- [A Survey of Machine Unlearning](https://mlsanity.com/paper/2209.02299/) (2022)
- [Unrolling SGD: Understanding Factors Influencing Machine Unlearning](https://mlsanity.com/paper/2109.13398/) (2021)
- [Towards Unbounded Machine Unlearning](https://mlsanity.com/paper/2302.09880/) (2023)
- [Membership Inference Attacks against Language Models via Neighbourhood Comparison](https://mlsanity.com/paper/2305.18462/) (2023)

## Built on by (most cited first, 30 of 43)

- [What makes unlearning hard and what to do about it](https://mlsanity.com/paper/2406.01257/) (2024)
- [Catastrophic Failure of LLM Unlearning via Quantization](https://mlsanity.com/paper/2410.16454/) (2024)
- [Position: LLM Unlearning Benchmarks are Weak Measures of Progress](https://mlsanity.com/paper/2410.02879/) (2024)
- [Revisiting Who's Harry Potter: Towards Targeted Unlearning from a Causal Intervention Perspective](https://mlsanity.com/paper/2407.16997/) (2024)
- [Towards Effective Evaluations and Comparisons for LLM Unlearning Methods](https://mlsanity.com/paper/2406.09179/) (2024)
- [Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning](https://mlsanity.com/paper/2506.01339/) (2025)
- [MU-Bench: A Multitask Multimodal Benchmark for Machine Unlearning](https://mlsanity.com/paper/2406.14796/) (2024)
- [Tool Unlearning for Tool-Augmented LLMs](https://mlsanity.com/paper/2502.01083/) (2025)
- [UnStar: Unlearning with Self-Taught Anti-Sample Reasoning for LLMs](https://mlsanity.com/paper/2410.17050/) (2024)
- [Mitigating Memorization In Language Models](https://mlsanity.com/paper/2410.02159/) (2024)
- [GRU: Mitigating the Trade-off between Unlearning and Retention for LLMs](https://mlsanity.com/paper/2503.09117/) (2025)
- [LLM Unlearning Reveals a Stronger-Than-Expected Coreset Effect in Current Benchmarks](https://mlsanity.com/paper/2504.10185/) (2025)
- [Ascent Fails to Forget](https://mlsanity.com/paper/2509.26427/) (2025)
- [Distillation Robustifies Unlearning](https://mlsanity.com/paper/2506.06278/) (2025)
- [SoK: Machine Unlearning for Large Language Models](https://mlsanity.com/paper/2506.09227/) (2025)
- [Operationalizing Data Minimization for Privacy-Preserving LLM Prompting](https://mlsanity.com/paper/2510.03662/) (2025)
- [Memorization Sinks: Isolating Memorization during LLM Training](https://mlsanity.com/paper/2507.09937/) (2025)
- [Scalability of memorization-based machine unlearning](https://mlsanity.com/paper/2410.16516/) (2024)
- [Erase or Hide? Suppressing Spurious Unlearning Neurons for Robust Unlearning](https://mlsanity.com/paper/2509.22263/) (2025)
- [The Erasure Illusion: Stress-Testing the Generalization of LLM Forgetting Evaluation](https://mlsanity.com/paper/2512.19025/) (2025)
- [Unlearning in- vs. out-of-distribution data in LLMs under gradient-based method](https://mlsanity.com/paper/2411.04388/) (2024)
- [DUSK: Do Not Unlearn Shared Knowledge](https://mlsanity.com/paper/2505.15209/) (2025)
- [Leveraging Per-Instance Privacy for Machine Unlearning](https://mlsanity.com/paper/2505.18786/) (2025)
- [REBEL: Hidden Knowledge Recovery via Evolutionary-Based Evaluation Loop](https://mlsanity.com/paper/2602.06248/) (2026)
- [Is your algorithm unlearning or untraining?](https://mlsanity.com/paper/2604.07962/) (2026)
- [LoReUn: Data Itself Implicitly Provides Cues to Improve Machine Unlearning](https://mlsanity.com/paper/2507.22499/) (2025)
- [RESTOR: Knowledge Recovery in Machine Unlearning](https://mlsanity.com/paper/2411.00204/) (2024)
- [A Lightweight Method to Disrupt Memorized Sequences in LLM](https://mlsanity.com/paper/2502.05159/) (2025)
- [Mitigating Memorization Where It Happens](https://mlsanity.com/paper/2602.08901/) (2026)
- [MIAT: Maneuver-Intention-Aware Transformer for Spatio-Temporal Trajectory Prediction](https://mlsanity.com/paper/2504.05059/) (2025)

## Abstract (arXiv)

LLMs have been found to memorize training textual sequences and regurgitate verbatim said sequences during text generation time. This fact is known to be the cause of privacy and related (e.g., copyright) problems. Unlearning in LLMs then takes the form of devising new algorithms that will properly deal with these side-effects of memorized data, while not hurting the model's utility. We offer a fresh perspective towards this goal, namely, that each textual sequence to be forgotten should be treated differently when being unlearned based on its degree of memorization within the LLM. We contribute a new metric for measuring unlearning quality, an adversarial attack showing that SOTA algorithms lacking this perspective fail for privacy, and two new unlearning methods based on Gradient Ascent and Task Arithmetic, respectively. A comprehensive performance evaluation across an extensive suite of NLP tasks then mapped the solution space, identifying the best solutions under different scales in model capacities and forget set sizes and quantified the gains of the new approaches.