MUSE: Machine Unlearning Six-Way Evaluation for Language Models

• URL: http://arxiv.org/abs/2407.06460v2
• Date: Sun, 14 Jul 2024 20:14:02 GMT
• Title: MUSE: Machine Unlearning Six-Way Evaluation for Language Models
• Authors: Weijia Shi, Jaechan Lee, Yangsibo Huang, Sadhika Malladi, Jieyu Zhao, Ari Holtzman, Daogao Liu, Luke Zettlemoyer, Noah A. Smith, Chiyuan Zhang,
• Abstract summary: 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.
• Score: 109.76505405962783
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Language models (LMs) are trained on vast amounts of text data, which may include private and copyrighted content. Data owners may request the removal of their data from a trained model due to privacy or copyright concerns. However, exactly unlearning only these datapoints (i.e., retraining with the data removed) is intractable in modern-day models. This has led to the development of many approximate unlearning algorithms. The evaluation of the efficacy of these algorithms has traditionally been narrow in scope, failing to precisely quantify the success and practicality of the algorithm from the perspectives of both the model deployers and the data owners. We address this issue by proposing MUSE, a comprehensive machine unlearning evaluation benchmark that enumerates six diverse desirable properties for unlearned models: (1) no verbatim memorization, (2) no knowledge memorization, (3) no privacy leakage, (4) utility preservation on data not intended for removal, (5) scalability with respect to the size of removal requests, and (6) sustainability over sequential unlearning requests. Using these criteria, we benchmark how effectively eight popular unlearning algorithms on 7B-parameter LMs can unlearn Harry Potter books and news articles. Our results demonstrate that most algorithms can prevent verbatim memorization and knowledge memorization to varying degrees, but only one algorithm does not lead to severe privacy leakage. Furthermore, existing algorithms fail to meet deployer's expectations because they often degrade general model utility and also cannot sustainably accommodate successive unlearning requests or large-scale content removal. Our findings identify key issues with the practicality of existing unlearning algorithms on language models, and we release our benchmark to facilitate further evaluations: muse-bench.github.io

Related papers

• RESTOR: Knowledge Recovery through Machine Unlearning [71.75834077528305]
  Large language models trained on web-scale corpora can memorize undesirable datapoints. Many machine unlearning methods have been proposed that aim to 'erase' these datapoints from trained models. We propose the RESTOR framework for machine unlearning based on the following dimensions.
  arXiv  Detail & Related papers  (2024-10-31T20:54:35Z)
• 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. 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)
• SIaM: Self-Improving Code-Assisted Mathematical Reasoning of Large Language Models [54.78329741186446]
  We propose a novel paradigm that uses a code-based critic model to guide steps including question-code data construction, quality control, and complementary evaluation. Experiments across both in-domain and out-of-domain benchmarks in English and Chinese demonstrate the effectiveness of the proposed paradigm.
  arXiv  Detail & Related papers  (2024-08-28T06:33:03Z)
• Gone but Not Forgotten: Improved Benchmarks for Machine Unlearning [0.0]
  We describe and propose alternative evaluation methods for machine unlearning algorithms. We show the utility of our alternative evaluations via a series of experiments of state-of-the-art unlearning algorithms on different computer vision datasets.
  arXiv  Detail & Related papers  (2024-05-29T15:53:23Z)
• Second-Order Information Matters: Revisiting Machine Unlearning for Large Language Models [1.443696537295348]
  Privacy leakage and copyright violation are still underexplored. Our unlearning algorithms are not only data-agnostic/model-agnostic but also proven to be robust in terms of utility preservation or privacy guarantee.
  arXiv  Detail & Related papers  (2024-03-13T18:57:30Z)
• 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)
• 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)
• Tight Bounds for Machine Unlearning via Differential Privacy [0.7252027234425334]
  We consider the so-called "right to be forgotten" by requiring that a trained model should be able to "unlearn" a number of points from the training data. We obtain tight bounds on the deletion capacity achievable by DP-based machine unlearning algorithms.
  arXiv  Detail & Related papers  (2023-09-02T09:55:29Z)
• 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.