Align-then-Unlearn: Embedding Alignment for LLM Unlearning

• URL: http://arxiv.org/abs/2506.13181v1
• Date: Mon, 16 Jun 2025 07:48:01 GMT
• Title: Align-then-Unlearn: Embedding Alignment for LLM Unlearning
• Authors: Philipp Spohn, Leander Girrbach, Jessica Bader, Zeynep Akata,
• Abstract summary: 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.
• Score: 41.94295877935867
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: As large language models (LLMs) are trained on massive datasets, they have raised significant privacy and ethical concerns due to their potential to inadvertently retain sensitive information. Unlearning seeks to selectively remove specific data from trained models, such as personal information or copyrighted content. Current approaches targeting specific output sequences at the token level often fail to achieve complete forgetting and remain susceptible to prompt rephrasing. We propose Align-then-Unlearn, a novel framework that performs unlearning in the semantic embedding space rather than directly on output tokens. Align-then-Unlearn first augments the LLM with an embedding prediction module trained to anticipate future context representations. Unlearning is then achieved by fine-tuning the model to minimize the similarity between these predicted embeddings and a target embedding that represents the concept to be removed. Initial results show that Align-then-Unlearn effectively removes targeted knowledge with minimal degradation in overall model utility. These findings suggest that embedding-based unlearning offers a promising and robust approach to removing conceptual knowledge. Our code is available at https://github.com/ExplainableML/align-then-unlearn.

Related papers

• Model Collapse Is Not a Bug but a Feature in Machine Unlearning for LLMs [44.8238758047607]
  Current unlearning methods for LLMs optimize on the private information they seek to remove by incorporating it into their training objectives.<n>We argue this not only risks reinforcing exposure to sensitive data, it also contradicts the principle of minimizing its use.<n>We propose a novel unlearning method - Partial Model Collapse (PMC), which does not require unlearning targets in the unlearning objective.
  arXiv  Detail & Related papers  (2025-07-06T03:08:49Z)
• Unlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model Outputs [19.08691637612329]
  Machine unlearning (MU) for large language models (LLMs) seeks to remove specific undesirable data or knowledge from a trained model.<n>We identify a new vulnerability post-unlearning: unlearning trace detection.<n>We show that forget-relevant prompts enable over 90% accuracy in detecting unlearning traces across all model sizes.
  arXiv  Detail & Related papers  (2025-06-16T21:03:51Z)
• 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)
• Catastrophic Failure of LLM Unlearning via Quantization [36.524827594501495]
  We show that applying quantization to models that have undergone unlearning can restore the "forgotten" information.<n>We find that for unlearning methods with utility constraints, the unlearned model retains an average of 21% of the intended forgotten knowledge in full precision.
  arXiv  Detail & Related papers  (2024-10-21T19:28:37Z)
• A Closer Look at Machine Unlearning for Large Language Models [46.245404272612795]
  Large language models (LLMs) may memorize sensitive or copyrighted content, raising privacy and legal concerns.<n>We discuss several issues in machine unlearning for LLMs and provide our insights on possible approaches.
  arXiv  Detail & Related papers  (2024-10-10T16:56:05Z)
• 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)
• Offset Unlearning for Large Language Models [49.851093293780615]
  delta-Unlearning is an offset unlearning framework for black-box LLMs.<n>We show that delta-Unlearning can effectively unlearn target data while maintaining similar or even stronger performance on general out-of-forget-scope tasks.
  arXiv  Detail & Related papers  (2024-04-17T03:39:51Z)
• Learn to Unlearn for Deep Neural Networks: Minimizing Unlearning Interference with Gradient Projection [56.292071534857946]
  Recent data-privacy laws have sparked interest in machine unlearning. Challenge is to discard information about the forget'' data without altering knowledge about remaining dataset. We adopt a projected-gradient based learning method, named as Projected-Gradient Unlearning (PGU) We provide empirically evidence to demonstrate that our unlearning method can produce models that behave similar to models retrained from scratch across various metrics even when the training dataset is no longer accessible.
  arXiv  Detail & Related papers  (2023-12-07T07:17:24Z)
• Unlearn What You Want to Forget: Efficient Unlearning for LLMs [92.51670143929056]
  Large language models (LLMs) have achieved significant progress from pre-training on and memorizing a wide range of textual data. This process might suffer from privacy issues and violations of data protection regulations. We propose an efficient unlearning framework that could efficiently update LLMs without having to retrain the whole model after data removals.
  arXiv  Detail & Related papers  (2023-10-31T03:35:59Z)
• Machine Unlearning of Features and Labels [72.81914952849334]
  We propose first scenarios for unlearning and labels in machine learning models. Our approach builds on the concept of influence functions and realizes unlearning through closed-form updates of model parameters.
  arXiv  Detail & Related papers  (2021-08-26T04:42:24Z)

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.