Learning What to Forget: Improving LLM Unlearning via Learned Token-Level Importance

• URL: http://arxiv.org/abs/2606.06320v1
• Date: Thu, 04 Jun 2026 15:56:32 GMT
• Title: Learning What to Forget: Improving LLM Unlearning via Learned Token-Level Importance
• Abstract summary: We introduce Alternating Token-Weighted Unlearning (ATWU), a lightweight framework that jointly learns token forget-specificity and model parameters during unlearning.<n>ATWU achieves state of the art forget-retain trade-offs, outperforming sample-level methods, probability-based token weightings, and auxiliary-model-based approaches.
• Score: 30.72675145829489
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Machine unlearning aims to remove targeted knowledge from a trained model while preserving its general capabilities. For autoregressive language models, not all tokens in a forget sample are equally relevant to forgetting. Existing approaches either ignore this heterogeneity or rely on auxiliary models, heuristics, or external annotations to estimate each token's relevance for forgetting. We instead characterize it through the interaction with the retain objective: a token is forget-specific to the extent that minimizing the forget loss on that token does not conflict with retain optimality. We formalize this perspective as a joint optimization problem over the model parameters and the token weights and show that, under a natural separation condition, the resulting objective recovers the oracle forget-specific token support. Motivated by this formulation, we introduce Alternating Token-Weighted Unlearning (ATWU), a lightweight framework that jointly learns token forget-specificity and model parameters during unlearning using a simple linear scorer over the hidden states, without external token level supervision. Across TOFU and RWKU, ATWU achieves state of the art forget-retain trade-offs, outperforming sample-level methods, probability-based token weighting heuristics, and auxiliary-model-based approaches. Moreover, the learned scores align substantially better with ground truth forget-specific spans, indicating that ATWU identifies semantically meaningful token level forgetting signals. Overall, our results suggest that retain conflict provides an effective criterion for identifying what language models should forget, enabling unsupervised learning of token level forget-specificity directly from model representations with minimal computational overhead.

Related papers

• Confess What You Know: Forget-Set Misalignment with Model Knowledge in LLM Unlearning [9.140696856930457]
  We term this gap forget-set misalignment and identify two cases.<n>In Under Unlearning, the forget set omits memorized information and leakage persists.<n>In Out-of-Knowledge Unlearning, the algorithm is driven to "forget" knowledge the model never learned, perturbing parameters and degrading utility.<n>We propose a data-blind framework that constructs model-aligned forget sets by eliciting and formalizing the model's memorized knowledge.
  arXiv  Detail & Related papers  (2026-09-01T02:47:43Z)
• SHRED: Retain-Set-Free Unlearning via Self-Distillation with Logit Demotion [39.17638540496959]
  SHRED (Self-distillation via High-surprisal-only Retain-set-free Entropy Demotion) is a retain-set-free unlearning method built on a key insight.<n>High-information tokens concentrate the model's memorized knowledge, while low-information tokens reflect general language competence.<n> SHRED is robust against relearning attacks and membership-inference attacks, and it maintains stable utility even after many sequential unlearning runs.
  arXiv  Detail & Related papers  (2026-05-08T09:25:18Z)
• MeGU: Machine-Guided Unlearning with Target Feature Disentanglement [73.49657372882082]
  We propose a novel framework that guides unlearning through concept-aware re-alignment.<n>MeGU enables controlled and selective forgetting, effectively mitigating both under-unlearning and over-unlearning.
  arXiv  Detail & Related papers  (2026-02-19T05:20:31Z)
• Towards Benign Memory Forgetting for Selective Multimodal Large Language Model Unlearning [49.274436951541425]
  Multimodal Large Language Models (MLLMs) achieve remarkable capabilities but can inadvertently memorize privacy-sensitive information.<n>Existing unlearning methods fail to achieve benign forgetting because they often degrade the model's general image understanding performance.<n>We propose the Sculpted Memory Forgetting Adapter (SMFA), which confines forgetting to targeted memory regions while preserving overall capabilities.
  arXiv  Detail & Related papers  (2025-11-25T11:22:45Z)
• LLM Unlearning on Noisy Forget Sets: A Study of Incomplete, Rewritten, and Watermarked Data [69.5099112089508]
  Large language models (LLMs) exhibit remarkable generative capabilities but raise ethical and security concerns by memorizing sensitive data.<n>This work presents the first study of unlearning under perturbed or low-fidelity forget data, referred to as noisy forget sets.<n>We find that unlearning remains surprisingly robust to perturbations, provided that core semantic signals are preserved.
  arXiv  Detail & Related papers  (2025-10-10T05:10:49Z)
• Direct Token Optimization: A Self-contained Approach to Large Language Model Unlearning [9.42887167048224]
  Machine unlearning is an emerging technique that removes the influence of a subset of training data (forget set) from a model without full retraining.<n>The key challenge lies in ensuring that the model completely forgets the knowledge of the forget set without compromising its overall utility.<n>We propose direct token optimization (DTO), a novel self-contained unlearning approach for large language models.
  arXiv  Detail & Related papers  (2025-09-30T18:05:06Z)
• Efficient Machine Unlearning via Influence Approximation [75.31015485113993]
  Influence-based unlearning has emerged as a prominent approach to estimate the impact of individual training samples on model parameters without retraining.<n>This paper establishes a theoretical link between memorizing (incremental learning) and forgetting (unlearning)<n>We introduce the Influence Approximation Unlearning algorithm for efficient machine unlearning from the incremental perspective.
  arXiv  Detail & Related papers  (2025-07-31T05:34:27Z)
• Not Every Token Needs Forgetting: Selective Unlearning to Limit Change in Utility in Large Language Model Unlearning [95.53571199301963]
  Conventional unlearning approaches indiscriminately update model parameters to forget all tokens in a target document.<n>We propose Selective Unlearning (SU), which identifies a critical subset of tokens within the forgetting set that is relevant to the unwanted information.<n>Experiments on two benchmarks and six baseline unlearning algorithms demonstrate that SU not only achieves effective unlearning on the targeted forget data, but also significantly preserves the model's utility in the retaining set.
  arXiv  Detail & Related papers  (2025-06-01T07:36:45Z)
• GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection [36.38245533018162]
  Large Language Models (LLMs) have demonstrated strong capabilities in memorizing vast amounts of knowledge across diverse domains.<n>Existing unlearning efforts typically fine-tune the model with resources such as forget data, retain data, and a calibration model.<n>We propose Generation-time Unlearning via Adaptive Restriction and Detection (GUARD), a framework that enables dynamic unlearning during LLM generation.
  arXiv  Detail & Related papers  (2025-05-19T16:26:58Z)
• Improving Input-label Mapping with Demonstration Replay for In-context Learning [67.57288926736923]
  In-context learning (ICL) is an emerging capability of large autoregressive language models. We propose a novel ICL method called Sliding Causal Attention (RdSca) We show that our method significantly improves the input-label mapping in ICL demonstrations.
  arXiv  Detail & Related papers  (2023-10-30T14:29:41Z)

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.