# What makes unlearning hard and what to do about it

arXiv: https://arxiv.org/abs/2406.01257 · HTML: https://mlsanity.com/paper/2406.01257/

## Key facts

- Cited by 89 papers in the map (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 31 of its 39 references that are in the map.
- First posted on arXiv 3 Jun 2024.

## Placed in

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

## Builds on (most cited first, 30 of 31)

- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Membership Inference Attacks From First Principles](https://mlsanity.com/paper/2112.03570/) (2021)
- [An Empirical Study of Example Forgetting during Deep Neural Network Learning](https://mlsanity.com/paper/1812.05159/) (2018)
- [Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks](https://mlsanity.com/paper/1911.04933/) (2019)
- [Certified Data Removal from Machine Learning Models](https://mlsanity.com/paper/1911.03030/) (2019)
- [What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation](https://mlsanity.com/paper/2008.03703/) (2020)
- [Making AI Forget You: Data Deletion in Machine Learning](https://mlsanity.com/paper/1907.05012/) (2019)
- [Does Learning Require Memorization? A Short Tale about a Long Tail](https://mlsanity.com/paper/1906.05271/) (2019)
- [SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation](https://mlsanity.com/paper/2310.12508/) (2023)
- [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)
- [Approximate Data Deletion from Machine Learning Models](https://mlsanity.com/paper/2002.10077/) (2020)
- [Machine Unlearning of Features and Labels](https://mlsanity.com/paper/2108.11577/) (2021)
- [Model Sparsity Can Simplify Machine Unlearning](https://mlsanity.com/paper/2304.04934/) (2023)
- [The Privacy Onion Effect: Memorization is Relative](https://mlsanity.com/paper/2206.10469/) (2022)
- [Measuring Forgetting of Memorized Training Examples](https://mlsanity.com/paper/2207.00099/) (2022)
- [Federated Unlearning via Class-Discriminative Pruning](https://mlsanity.com/paper/2110.11794/) (2021)
- [Characterizing Structural Regularities of Labeled Data in Overparameterized Models](https://mlsanity.com/paper/2002.03206/) (2020)
- [Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of Privacy](https://mlsanity.com/paper/2403.01218/) (2024)
- [Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win the Jackpot?](https://mlsanity.com/paper/2107.00166/) (2021)
- [Unraveling Meta-Learning: Understanding Feature Representations for Few-Shot Tasks](https://mlsanity.com/paper/2002.06753/) (2020)
- [Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearning](https://mlsanity.com/paper/2403.07362/) (2024)
- [Distribution Density, Tails, and Outliers in Machine Learning: Metrics and Applications](https://mlsanity.com/paper/1910.13427/) (2019)

## Built on by (most cited first, 30 of 89)

- [Are we making progress in unlearning? Findings from the first NeurIPS unlearning competition](https://mlsanity.com/paper/2406.09073/) (2024)
- [To Forget or Not? Towards Practical Knowledge Unlearning for Large Language Models](https://mlsanity.com/paper/2407.01920/) (2024)
- [LUME: LLM Unlearning with Multitask Evaluations](https://mlsanity.com/paper/2502.15097/) (2025)
- [Are We Truly Forgetting? A Critical Re-examination of Machine Unlearning Evaluation Protocols](https://mlsanity.com/paper/2503.06991/) (2025)
- [LLM Unlearning Reveals a Stronger-Than-Expected Coreset Effect in Current Benchmarks](https://mlsanity.com/paper/2504.10185/) (2025)
- [From Dormant to Deleted: Tamper-Resistant Unlearning Through Weight-Space Regularization](https://mlsanity.com/paper/2505.22310/) (2025)
- [Distillation Robustifies Unlearning](https://mlsanity.com/paper/2506.06278/) (2025)
- [Machine Unlearning under Retain-Forget Entanglement](https://mlsanity.com/paper/2603.26569/) (2026)
- [Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning](https://mlsanity.com/paper/2412.08559/) (2024)
- [MMTABREAL: Real-World Benchmark for Multimodal Table Understanding](https://mlsanity.com/paper/2505.21771/) (2025)
- [BalDRO: A Distributionally Robust Optimization based Framework for Large Language Model Unlearning](https://mlsanity.com/paper/2601.09172/) (2026)
- [Position: Bridge the Gaps between Machine Unlearning and AI Regulation](https://mlsanity.com/paper/2502.12430/) (2025)
- [Redirection for Erasing Memory (REM): Towards a universal unlearning method for corrupted data](https://mlsanity.com/paper/2505.17730/) (2025)
- [The Right to be Forgotten in Pruning: Unveil Machine Unlearning on Sparse Models](https://mlsanity.com/paper/2507.18725/) (2025)
- [Contrastive Representation Shaping for LLM Unlearning](https://mlsanity.com/paper/2601.22028/) (2026)
- [Attention Smoothing Is All You Need For Unlearning](https://mlsanity.com/paper/2603.01285/) (2026)
- [Improved Localized Machine Unlearning Through the Lens of Memorization](https://mlsanity.com/paper/2412.02432/) (2024)
- [Trustworthy Machine Learning via Memorization and the Granular Long-Tail: A Survey on Interactions, Tradeoffs, and Beyond](https://mlsanity.com/paper/2503.07501/) (2025)
- [Not All Tokens Are Meant to Be Forgotten](https://mlsanity.com/paper/2506.03142/) (2025)
- [Scalability of memorization-based machine unlearning](https://mlsanity.com/paper/2410.16516/) (2024)
- [Unlearning Personal Data from a Single Image](https://mlsanity.com/paper/2407.12069/) (2024)
- [BTBR: A Bayesian-Theory-Driven Probabilistic-Fuzzy Framework for Implicit Bias Removal in Large Language Models](https://mlsanity.com/paper/2408.10608/) (2024)
- [Leveraging Per-Instance Privacy for Machine Unlearning](https://mlsanity.com/paper/2505.18786/) (2025)
- [Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy](https://mlsanity.com/paper/2507.20573/) (2025)
- [CoUn: Empowering Machine Unlearning via Contrastive Learning](https://mlsanity.com/paper/2509.16391/) (2025)
- [MUSO: Achieving Exact Machine Unlearning in Over-Parameterized Regimes](https://mlsanity.com/paper/2410.08557/) (2024)
- [Tackling Fake Forgetting through Uncertainty Quantification](https://mlsanity.com/paper/2501.19403/) (2025)
- [Group-robust Machine Unlearning](https://mlsanity.com/paper/2503.09330/) (2025)
- [Towards Efficient and Exact Forgetting Services in Pre-Trained-Model-based Continual Learning](https://mlsanity.com/paper/2505.12239/) (2025)
- [LoReUn: Data Itself Implicitly Provides Cues to Improve Machine Unlearning](https://mlsanity.com/paper/2507.22499/) (2025)

## Abstract (arXiv)

Machine unlearning is the problem of removing the effect of a subset of training data (the ''forget set'') from a trained model without damaging the model's utility e.g. to comply with users' requests to delete their data, or remove mislabeled, poisoned or otherwise problematic data. With unlearning research still being at its infancy, many fundamental open questions exist: Are there interpretable characteristics of forget sets that substantially affect the difficulty of the problem? How do these characteristics affect different state-of-the-art algorithms? With this paper, we present the first investigation aiming to answer these questions. We identify two key factors affecting unlearning difficulty and the performance of unlearning algorithms. Evaluation on forget sets that isolate these identified factors reveals previously-unknown behaviours of state-of-the-art algorithms that don't materialize on random forget sets. Based on our insights, we develop a framework coined Refined-Unlearning Meta-algorithm (RUM) that encompasses: (i) refining the forget set into homogenized subsets, according to different characteristics; and (ii) a meta-algorithm that employs existing algorithms to unlearn each subset and finally delivers a model that has unlearned the overall forget set. We find that RUM substantially improves top-performing unlearning algorithms. Overall, we view our work as an important step in (i) deepening our scientific understanding of unlearning and (ii) revealing new pathways to improving the state-of-the-art.