Is your algorithm unlearning or untraining?

• URL: http://arxiv.org/abs/2604.07962v1
• Date: Thu, 09 Apr 2026 08:24:52 GMT
• Title: Is your algorithm unlearning or untraining?
• Abstract summary: We argue that the term unlearning'' has been overloaded, with different research efforts spanning two distinct problem formulations.<n>We identify two notions that we identify as unlearning and untraining, illustrated in Figure 1.<n>We discuss technical definitions of these problems and map problem settings studied in the literature to each.
• Score: 57.25293122855155
• License: http://creativecommons.org/licenses/by/4.0/
• 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''.

Related papers

• FaLW: A Forgetting-aware Loss Reweighting for Long-tailed Unlearning [24.734154431191538]
  FaLW is a plug-and-play, instance-wise dynamic loss reweighting method.<n>It assesses the unlearning state of each sample by comparing its predictive probability to the distribution of unseen data from the same class.<n>Experiments demonstrate that FaLW achieves superior performance.
  arXiv  Detail & Related papers  (2026-01-26T16:21:01Z)
• SoK: Machine Unlearning for Large Language Models [14.88062383081161]
  Large language model (LLM) unlearning has become a critical topic in machine learning.<n>We propose a new taxonomy based on the intention of unlearning.
  arXiv  Detail & Related papers  (2025-06-10T20:30:39Z)
• Adversarial Machine Unlearning [26.809123658470693]
  This paper focuses on the challenge of machine unlearning, aiming to remove the influence of specific training data on machine learning models. Traditionally, the development of unlearning algorithms runs parallel with that of membership inference attacks (MIA), a type of privacy threat. We propose a game-theoretic framework that integrates MIAs into the design of unlearning algorithms.
  arXiv  Detail & Related papers  (2024-06-11T20:07:22Z)
• What makes unlearning hard and what to do about it [3.2140380913122195]
  We identify two key factors affecting unlearning difficulty and the performance of unlearning algorithms. 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.
  arXiv  Detail & Related papers  (2024-06-03T12:14:47Z)
• Mitigating Reversal Curse in Large Language Models via Semantic-aware Permutation Training [57.771940716189114]
  We show that large language models (LLMs) suffer from the "reversal curse" The root cause of the reversal curse lies in the different word order between the training and inference stage. We propose Semantic-aware Permutation Training (SPT) to address this issue.
  arXiv  Detail & Related papers  (2024-03-01T18:55:20Z)
• Ticketed Learning-Unlearning Schemes [57.89421552780526]
  We propose a new ticketed model for learning--unlearning. We provide space-efficient ticketed learning--unlearning schemes for a broad family of concept classes.
  arXiv  Detail & Related papers  (2023-06-27T18:54:40Z)
• Characterizing Datapoints via Second-Split Forgetting [93.99363547536392]
  We propose $$-second-$split$ $forgetting$ $time$ (SSFT), a complementary metric that tracks the epoch (if any) after which an original training example is forgotten. We demonstrate that $mislabeled$ examples are forgotten quickly, and seemingly $rare$ examples are forgotten comparatively slowly. SSFT can (i) help to identify mislabeled samples, the removal of which improves generalization; and (ii) provide insights about failure modes.
  arXiv  Detail & Related papers  (2022-10-26T21:03:46Z)
• The Extraordinary Failure of Complement Coercion Crowdsourcing [50.599433903377374]
  Crowdsourcing has eased and scaled up the collection of linguistic annotation in recent years. We aim to collect annotated data for this phenomenon by reducing it to either of two known tasks: Explicit Completion and Natural Language Inference. In both cases, crowdsourcing resulted in low agreement scores, even though we followed the same methodologies as in previous work.
  arXiv  Detail & Related papers  (2020-10-12T19:04:04Z)
• Learning What Makes a Difference from Counterfactual Examples and Gradient Supervision [57.14468881854616]
  We propose an auxiliary training objective that improves the generalization capabilities of neural networks. We use pairs of minimally-different examples with different labels, a.k.a counterfactual or contrasting examples, which provide a signal indicative of the underlying causal structure of the task. Models trained with this technique demonstrate improved performance on out-of-distribution test sets.
  arXiv  Detail & Related papers  (2020-04-20T02:47:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.