cs.LGApr 9, 2026

Is your algorithm unlearning or untraining?

Authors: Eleni Triantafillou, Ahmed Imtiaz Humayun, Monica Ribero, Alexander Matt Turner, Michael C. Mozer, Georgios Kaissis

Organizations: Google · Hasso Plattner Institute

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

As models are getting larger and are trained on increasing amounts of data, there has been an explosion of interest into how we can delete'' specific data points or behaviours from a trained model, after the fact. This goal has been referred to as machine unlearning''. In this note, we argue that the term unlearning'' has been overloaded, with different research efforts spanning two distinct problem formulations, but without that distinction having been observed or acknowledged in the literature. This causes various issues, including ambiguity around when an algorithm is expected to work, use of inappropriate metrics and baselines when comparing different algorithms to one another, difficulty in interpreting results, as well as missed opportunities for pursuing critical research directions. In this note, we address this issue by establishing a fundamental distinction between two notions that we identify as \unlearning and \untraining, illustrated in Figure 1. In short, \untraining aims to reverse the effect of having trained on a given forget set, i.e. to remove the influence that that specific forget set examples had on the model during training. On the other hand, the goal of \unlearning is not just to remove the influence of those given examples, but to use those examples for the purpose of more broadly removing the entire underlying distribution from which those examples were sampled (e.g. the concept or behaviour that those examples represent). We discuss technical definitions of these problems and map problem settings studied in the literature to each. We hope to initiate discussions on disambiguating technical definitions and identify a set of overlooked research questions, as we believe that this a key missing step for accelerating progress in the field of unlearning''.

Figures & tables

Figure 1: Illustration of the difference between Unlearning and Untraining on a forget set S\mathcal{S} . The different shapes correspond to data points in a dataset D\mathcal{D} . A shape is white if the model predicts it correctly and black otherwise. In the middle, we depict the predictions of the original model that was trained on all of D\mathcal{D} , before any Unlearning or Untraining is carried out. This model predicts correctly on all of its training set. On the left, we show the predictions of the model obtained by perfectly Untraining S\mathcal{S} , which matches the behaviour of a model trained on D∖S\mathcal{D}\setminus\mathcal{S} – i.e. a model trained on all of D\mathcal{D} except for the star and the two circles that belong to the forget set S\mathcal{S} . Notice that the Untrained model still predicts the circles correctly. This is because there are several other circles in the remaining dataset from where the model trained on D∖S\mathcal{D}\setminus\mathcal{S} can learn about circles. On the other hand, the star that was in the forget set is no longer predicted correctly, as there are fewer other stars in the dataset. On the right, we show the predictions of the model obtained by Unlearning the “behaviour” underlying S\mathcal{S} , where the “behaviour” in this case is “being a circle or a star”. The unlearned model makes incorrect predictions on all examples of that behaviour.
More in this topic

Machine Unlearning

Machine unlearning removes the influence of selected data or concepts from trained models while preserving useful behavior and avoiding full retraining.

See all 343 papers

Explore similar work

CardsList
Oct 7, 2026

Why Forget-Only Unlearning Needs Memorization

Machine unlearning asks for a deletion algorithm whose output is close to retraining from scratch without the selected forget examples. In this work, we study forget-only unlearning, where the deletion algorithm receives only the trained model and the examples to forget, with no retained data or extra training information. We ask whether forget-only unlearning is always possible. We first show that this depends on the learning method: different datasets can produce the same trained model but require very different outputs after the same examples are removed. Using this observation, we derive lower bounds on how accurately unlearning can match retraining and instantiate them for several standard learning algorithms. We then ask what must be true when forget-only unlearning succeeds. To this end, we derive lower bounds on what an algorithm must memorize about the training data to handle arbitrary deletion requests. For simple threshold learners, the required information can be as large as the entire dataset, even though ordinary training keeps only one boundary point. Overall, our results show that information discarded during ordinary learning may be needed later for deletion, so models designed for forget-only unlearning may need to retain more information than standard training does.

Luka Radić, Vikrant Singhal, Amartya Sanyal

Department of Computer Science, University of Copenhagen

Machine Unlearning
AskPDF
May 8, 2026

Position: The Term "Machine Unlearning" Is Overused in LLMs

Large language models increasingly face demands to "forget" training data, knowledge, or behaviors due to regulatory deletion obligations, copyright/licensing disputes, and safety or product-policy requirements. This position paper argues that machine unlearning is overused as a term in LLM research and should be reserved for dataset-defined deletion: removing the training influence of a precisely specified forget set such that the resulting model is approximately indistinguishable from retraining without that data. We contend that many tasks currently labeled "unlearning" (e.g., refusal for harmful requests, entity/knowledge removal, or targeted suppression) pursue different, often policy-dependent objectives and therefore require different terminology and baselines (e.g., alignment, suppression, editing, obfuscation). We further argue that this confusion is not cosmetic: because papers make different implicit guarantees under the same label, metrics and benchmarks are frequently reused outside their intended scope, rewarding surface-level non-disclosure (e.g., low ROUGE/forget accuracy) even when retraining-equivalence is not tested and derived capabilities remain. We conclude by calling for stricter terminology tied to explicit guarantees and reference models, and for evaluations that match the claimed objective.

Sangyeon Yoon, Yeachan Jun, Albert No

Department of Artificial Intelligence, Yonsei University, Seoul, Korea.

LLM EvaluationMachine UnlearningLLM Unlearning
AskPDF
Oct 3, 2024

Instance-Level Difficulty: A Missing Perspective in Machine Unlearning

Current research on deep machine unlearning primarily focuses on improving or evaluating the overall effectiveness of unlearning methods while overlooking the varying difficulty of unlearning individual training samples. As a result, the broader feasibility of machine unlearning remains under-explored. This paper studies the cruxes that make machine unlearning difficult through a thorough instance-level unlearning performance analysis over various unlearning algorithms and datasets. In particular, we summarize four factors that make unlearning a data point difficult, and we empirically show that these factors are independent of a specific unlearning algorithm but only relevant to the target model and its training data. Given these findings, we argue that machine unlearning research should pay attention to the instance-level difficulty of unlearning.

Hammad Rizwan, Mahtab Sarvmaili, Hassan Sajjad +1

Department of Computer Science, Dalhousie University, Canada.

Machine UnlearningMachine Unlearning Evaluation
AskPDF