Erased, but Not Gone: Output Forgetting Is Not True Forgetting

• URL: http://arxiv.org/abs/2606.25001v1
• Date: Tue, 23 Jun 2026 16:23:53 GMT
• Title: Erased, but Not Gone: Output Forgetting Is Not True Forgetting
• Abstract summary: We show that standard output-level evaluation can systematically overestimate the success of unlearning.<n>Under this stronger lens, current methods often appear forgotten at the output layer while exhibiting a structured mismatch relative to retraining.<n>This structured mismatch is characterized by forget/retain asymmetry, directional mismatch, and concentrated residuals along retraining-related directions.
• Score: 9.095371772236932
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Machine unlearning (MU) is commonly judged by output forgetting, such as low forget-set accuracy or reduced logit-level membership inference. But if output-level success can coexist with retraining-inconsistent residuals in representation space, what kind of forgetting are current evaluations actually certifying? We study this question through retraining-consistent representation forgetting, using the retrained model (i.e., trained from scratch without the forget data) as an operational reference for correct forgetting. Across multiple unlearning methods, datasets, and models, our theoretical analysis and empirical results show that standard output-level evaluation can systematically overestimate the success of unlearning. Under this stronger lens, current methods often appear forgotten at the output layer while exhibiting a structured mismatch relative to retraining. They partially align with retraining on forget samples, remain more inconsistent on retain samples, and leave residual discrepancy concentrated along retraining-related directions rather than diffuse in representation space. This structured mismatch is characterized by forget/retain asymmetry, directional mismatch, and concentrated residuals along retraining-related directions. These results suggest that current MU is often evaluated for apparent forgetting rather than retraining-consistent forgetting. More broadly, retraining reveals what output forgetting hides.

Related papers

• When to Review: Spaced Repetition for Continual Pre-Training of Language Models [1.0262304700896199]
  Existing replay methods often choose a global old/new mixture and sample uniformly, ignoring that examples differ in how quickly they are forgotten.<n>We formulate continual pre-training as adaptive review scheduling: the training loop should decide not only how much history to replay, but which examples should return at each step.<n>We introduce Spaced Repetition Training (SRT), a continual learning framework inspired by cognitive science, which schedules sample-rehearsal using the SuperMemo-2 (SM-2) algorithm.
  arXiv  Detail & Related papers  (2026-08-18T08:51:47Z)
• Fast Unlearning at Scale via Margin Self-Correction [52.46927918952516]
  Language-model unlearning updates a trained model to behave as if it had not seen selected training examples.<n>MASC achieves a competitive forget-retain trade-off at a fraction of the computational cost of existing baselines.
  arXiv  Detail & Related papers  (2026-06-01T21:49:54Z)
• Forgetting Has Neighbors: Localized Collateral Forgetting in Machine Unlearning [28.628342735283752]
  Machine unlearning aims to remove the influence of selected training examples without full retraining.<n>Standard evaluations often summarize unlearning quality with aggregate metrics, such as accuracy- and forgetting-based scores.<n>We study this failure mode at the example level by comparing the predictions of an unlearned model to those of the model retrained after deletion.
  arXiv  Detail & Related papers  (2026-05-29T13:48:06Z)
• Approximate Machine Unlearning through Manifold Representation Forgetting Guided by Self Mode Connectivity [27.485504993716884]
  Machine unlearning enforces the right to be forgotten.<n>ManiF-SMC tackles the manifold representation-based unlearning problem.<n>It achieves unlearning effectiveness comparable to state-of-the-art approximate methods.
  arXiv  Detail & Related papers  (2026-05-20T01:28:42Z)
• Not Every Subject Should Stay: Machine Unlearning for Noisy Engagement Recognition [53.005382593686356]
  Engagement recognition datasets are typically subject-indexed and often contain noisy, subjective supervision.<n>We study this setting through subject-level machine unlearning as a post-hoc sanitization mechanism for engagement recognition.
  arXiv  Detail & Related papers  (2026-05-06T10:03:06Z)
• Refinement Provenance Inference: Detecting LLM-Refined Training Prompts from Model Behavior [58.751981587234916]
  This paper formalizes the Refinement Provenance Inference (RPI) audit task as Refinement Provenance Inference (RPI)<n>We propose RePro, a logit-based framework that fuses teacher-forced likelihood features with logit-ranking signals.<n>During training, RePro learns a transferable representation via shadow fine-tuning, and uses a lightweight linear head to infer provenance on unseen victims without training-data access.
  arXiv  Detail & Related papers  (2026-01-05T10:16:41Z)
• Rethinking Classifier Re-Training in Long-Tailed Recognition: A Simple Logits Retargeting Approach [102.0769560460338]
  We develop a simple logits approach (LORT) without the requirement of prior knowledge of the number of samples per class. Our method achieves state-of-the-art performance on various imbalanced datasets, including CIFAR100-LT, ImageNet-LT, and iNaturalist 2018.
  arXiv  Detail & Related papers  (2024-03-01T03:27:08Z)
• Enhancing Consistency and Mitigating Bias: A Data Replay Approach for Incremental Learning [93.90047628101155]
  Deep learning systems are prone to catastrophic forgetting when learning from a sequence of tasks.<n>To address this, some methods propose replaying data from previous tasks during new task learning.<n>However, it is not expected in practice due to memory constraints and data privacy issues.
  arXiv  Detail & Related papers  (2024-01-12T12:51:12Z)
• Noisy Correspondence Learning with Self-Reinforcing Errors Mitigation [63.180725016463974]
  Cross-modal retrieval relies on well-matched large-scale datasets that are laborious in practice. We introduce a novel noisy correspondence learning framework, namely textbfSelf-textbfReinforcing textbfErrors textbfMitigation (SREM)
  arXiv  Detail & Related papers  (2023-12-27T09:03:43Z)
• Class-Adaptive Self-Training for Relation Extraction with Incompletely Annotated Training Data [43.46328487543664]
  Relation extraction (RE) aims to extract relations from sentences and documents. Recent studies showed that many RE datasets are incompletely annotated. This is known as the false negative problem in which valid relations are falsely annotated as 'no_relation'
  arXiv  Detail & Related papers  (2023-06-16T09:01:45Z)
• Unsupervised Dense Retrieval with Relevance-Aware Contrastive Pre-Training [81.3781338418574]
  We propose relevance-aware contrastive learning. We consistently improve the SOTA unsupervised Contriever model on the BEIR and open-domain QA retrieval benchmarks. Our method can not only beat BM25 after further pre-training on the target corpus but also serves as a good few-shot learner.
  arXiv  Detail & Related papers  (2023-06-05T18:20:27Z)

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.