Not Every Token Needs Forgetting: Selective Unlearning to Limit Change in Utility in Large Language Model Unlearning

• URL: http://arxiv.org/abs/2506.00876v1
• Date: Sun, 01 Jun 2025 07:36:45 GMT
• Title: Not Every Token Needs Forgetting: Selective Unlearning to Limit Change in Utility in Large Language Model Unlearning
• Authors: Yixin Wan, Anil Ramakrishna, Kai-Wei Chang, Volkan Cevher, Rahul Gupta,
• Abstract summary: 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.
• Score: 95.53571199301963
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Model (LLM) unlearning has recently gained significant attention, driven by the need to remove unwanted information, such as private, sensitive, or copyrighted content, from LLMs. However, conventional unlearning approaches indiscriminately update model parameters to forget all tokens in a target document, including common tokens (e.g., pronouns, prepositions, general nouns) that carry general knowledge. In this paper, we highlight that not every token needs forgetting. We propose Selective Unlearning (SU), which identifies a critical subset of tokens within the forgetting set that is relevant to the unwanted information, and unlearns only those tokens. 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.

Related papers

• Align-then-Unlearn: Embedding Alignment for LLM Unlearning [41.94295877935867]
  Unlearning seeks to selectively remove specific data from trained models, such as personal information or copyrighted content.<n>We propose Align-then-Unlearn, a novel framework that performs unlearning in the semantic embedding space.
  arXiv  Detail & Related papers  (2025-06-16T07:48:01Z)
• Not All Tokens Are Meant to Be Forgotten [13.060635265281864]
  Large Language Models (LLMs) exhibit remarkable human-level language understanding, reasoning, and decision-making abilities.<n>LLMs tend to memorize unwanted information, such as private or copyrighted content, raising significant privacy and legal concerns.
  arXiv  Detail & Related papers  (2025-06-03T17:59:05Z)
• UniErase: Unlearning Token as a Universal Erasure Primitive for Language Models [54.75551043657238]
  We introduce UniErase, a novel unlearning paradigm that employs learnable parametric suffix (unlearning token) to steer language models toward targeted forgetting behaviors.<n>UniErase achieves state-of-the-art (SOTA) performance across batch, sequential, and precise unlearning under fictitious and real-world knowledge settings.
  arXiv  Detail & Related papers  (2025-05-21T15:53:28Z)
• 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)
• CodeUnlearn: Amortized Zero-Shot Machine Unlearning in Language Models Using Discrete Concept [5.345828824625758]
  We propose a novel amortized unlearning approach using codebook features and Sparse Autoencoders (SAEs) By leveraging a bottleneck to decompose the activation space and regulate information flow, our method efficiently unlearns targeted information while preserving the model's performance on unrelated data.
  arXiv  Detail & Related papers  (2024-10-08T10:26:22Z)
• STORE: Streamlining Semantic Tokenization and Generative Recommendation with A Single LLM [59.08493154172207]
  We propose a unified framework to streamline the semantic tokenization and generative recommendation process. We formulate semantic tokenization as a text-to-token task and generative recommendation as a token-to-token task, supplemented by a token-to-text reconstruction task and a text-to-token auxiliary task. All these tasks are framed in a generative manner and trained using a single large language model (LLM) backbone.
  arXiv  Detail & Related papers  (2024-09-11T13:49:48Z)
• MUSE: Machine Unlearning Six-Way Evaluation for Language Models [109.76505405962783]
  Language models (LMs) are trained on vast amounts of text data, which may include private and copyrighted content. We propose MUSE, a comprehensive machine unlearning evaluation benchmark. We benchmark how effectively eight popular unlearning algorithms can unlearn Harry Potter books and news articles.
  arXiv  Detail & Related papers  (2024-07-08T23:47:29Z)
• SEP: Self-Enhanced Prompt Tuning for Visual-Language Model [93.94454894142413]
  We introduce a novel approach named Self-Enhanced Prompt Tuning (SEP) SEP explicitly incorporates discriminative prior knowledge to enhance both textual-level and visual-level embeddings. Comprehensive evaluations across various benchmarks and tasks confirm SEP's efficacy in prompt tuning.
  arXiv  Detail & Related papers  (2024-05-24T13:35:56Z)
• TOFU: A Task of Fictitious Unlearning for LLMs [99.92305790945507]
  Large language models trained on massive corpora of data from the web can reproduce sensitive or private data raising both legal and ethical concerns. Unlearning, or tuning models to forget information present in their training data, provides us with a way to protect private data after training. We present TOFU, a benchmark aimed at helping deepen our understanding of unlearning.
  arXiv  Detail & Related papers  (2024-01-11T18:57:12Z)
• Self-Evolution Learning for Discriminative Language Model Pretraining [103.57103957631067]
  Self-Evolution learning (SE) is a simple and effective token masking and learning method. SE focuses on learning the informative yet under-explored tokens and adaptively regularizes the training by introducing a novel Token-specific Label Smoothing approach.
  arXiv  Detail & Related papers  (2023-05-24T16:00:54Z)
• LabelPrompt: Effective Prompt-based Learning for Relation Classification [31.291466190218912]
  This paper presents a novel prompt-based learning method, namely LabelPrompt, for the relation classification task. Motivated by the intuition to GIVE MODEL CHOICES!'', we first define additional tokens to represent relation labels, which regard these tokens as the verbaliser with semantic initialisation. Then, to mitigate inconsistency between predicted relations and given entities, we implement an entity-aware module with contrastive learning.
  arXiv  Detail & Related papers  (2023-02-16T04:06:25Z)

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.