English
Related papers

Related papers: Auditing Language Model Unlearning via Information…

200 papers

Machine unlearning offers a practical alternative to avoid full model re-training by approximately removing the influence of specific user data. While existing methods certify unlearning via statistical indistinguishability from re-trained…

Machine Learning · Computer Science 2026-02-02 Hsiang Hsu , Pradeep Niroula , Zichang He , Ivan Brugere , Freddy Lecue , Chun-Fu Chen

Large Language Models' knowledge of how to perform cyber-security attacks, create bioweapons, and manipulate humans poses risks of misuse. Previous work has proposed methods to unlearn this knowledge. Historically, it has been unclear…

Machine Learning · Computer Science 2025-02-10 Aghyad Deeb , Fabien Roger

Machine unlearning is a process to remove specific data points from a trained model while maintaining the performance on the retain data, addressing privacy or legal requirements. Despite its importance, existing unlearning evaluations tend…

Machine Learning · Computer Science 2026-01-30 Yongwoo Kim , Sungmin Cha , Donghyun Kim

The framework of Partial Information Decomposition (PID) unveils complex nonlinear interactions in network systems by dissecting the mutual information (MI) between a target variable and several source variables. While PID measures have…

Data Analysis, Statistics and Probability · Physics 2024-09-23 Chiara Barà , Yuri Antonacci , Marta Iovino , Ivan Lazic , Luca Faes

Machine unlearning poses challenges in removing mislabeled, contaminated, or problematic data from a pretrained model. Current unlearning approaches and evaluation metrics are solely focused on model predictions, which limits insight into…

Machine Learning · Computer Science 2026-04-13 Khoa Tran , Simon S. Woo

Machine unlearning requires removing the information of forgetting data while keeping the necessary information of remaining data. Despite recent advancements in this area, existing methodologies mainly focus on the effect of removing…

Machine Learning · Computer Science 2024-02-01 Shaofei Shen , Chenhao Zhang , Alina Bialkowski , Weitong Chen , Miao Xu

Unlearning in large language models (LLMs) aims to remove specified data, but its efficacy is typically assessed with task-level metrics like accuracy and perplexity. We show that these metrics can be misleading, as models can appear to…

Computation and Language · Computer Science 2026-05-19 Xiaoyu Xu , Xiang Yue , Yang Liu , Qingqing Ye , Huadi Zheng , Peizhao Hu , Minxin Du , Haibo Hu

The partial information decomposition (PID) framework is concerned with decomposing the information that a set of (two or more) random variables (the sources) has about another variable (the target) into three types of information: unique,…

Information Theory · Computer Science 2025-02-28 André F. C. Gomes , Mário A. T. Figueiredo

Machine unlearning is becoming essential for building trustworthy and compliant language models. Yet unlearning success varies considerably across individual samples: some are reliably erased, while others persist despite the same…

Machine Learning · Computer Science 2026-01-15 Jiali Cheng , Ziheng Chen , Chirag Agarwal , Hadi Amiri

The growing use of large language models in sensitive domains has exposed a critical weakness: the inability to ensure that private information can be permanently forgotten. Yet these systems still lack reliable mechanisms to guarantee that…

Machine Learning · Computer Science 2025-11-14 James Jin Kang , Dang Bui , Thanh Pham , Huo-Chong Ling

The partial information decomposition (PID) is perhaps the leading proposal for resolving information shared between a set of sources and a target into redundant, synergistic, and unique constituents. Unfortunately, the PID framework has…

Statistical Mechanics · Physics 2018-10-30 Ryan G. James , Jeffrey Emenheiser , James P. Crutchfield

Given the prevalence of large language models (LLMs) and the prohibitive cost of training these models from scratch, dynamically forgetting specific knowledge e.g., private or proprietary, without retraining the model has become an…

Computation and Language · Computer Science 2024-08-09 Tyler Lizzo , Larry Heck

Large language models (LLMs) acquire a large amount of knowledge through pre-training on vast and diverse corpora. While this endows LLMs with strong capabilities in generation and reasoning, it amplifies risks associated with sensitive,…

Cryptography and Security · Computer Science 2026-02-25 Ce Fang , Zhikun Zhang , Min Chen , Qing Liu , Lu Zhou , Zhe Liu , Yunjun Gao

Large language models (LLMs) exhibit remarkable generative capabilities but raise ethical and security concerns by memorizing sensitive data, reinforcing biases, and producing harmful content. These risks have spurred interest in LLM…

Machine Learning · Computer Science 2025-10-13 Changsheng Wang , Yihua Zhang , Dennis Wei , Jinghan Jia , Pin-Yu Chen , Sijia Liu

Fine-tuning-based unlearning methods prevail for preventing targeted harmful, sensitive, or copyrighted information within large language models while preserving overall capabilities. However, the true effectiveness of these methods is…

Computation and Language · Computer Science 2024-10-16 Yihuai Hong , Yuelin Zou , Lijie Hu , Ziqian Zeng , Di Wang , Haiqin Yang

Pretrained Language Models (LMs) memorize a vast amount of knowledge during initial pretraining, including information that may violate the privacy of personal lives and identities. Previous work addressing privacy issues for language…

Computation and Language · Computer Science 2022-12-20 Joel Jang , Dongkeun Yoon , Sohee Yang , Sungmin Cha , Moontae Lee , Lajanugen Logeswaran , Minjoon Seo

Since the recent advent of regulations for data protection (e.g., the General Data Protection Regulation), there has been increasing demand in deleting information learned from sensitive data in pre-trained models without retraining from…

Machine Learning · Computer Science 2024-01-17 Sungmin Cha , Sungjun Cho , Dasol Hwang , Honglak Lee , Taesup Moon , Moontae Lee

Large Language Models (LLMs) offer extensive knowledge across various domains, but they may inadvertently memorize sensitive, unauthorized, or malicious data, such as personal information in the medical and financial sectors. Machine…

Computation and Language · Computer Science 2024-10-16 YuXuan Wu , Bonaventure F. P. Dossou , Dianbo Liu

Recent advances in machine learning, particularly in Natural Language Processing (NLP), have produced powerful models trained on vast datasets. However, these models risk leaking sensitive information, raising privacy concerns. In response,…

Machine Learning · Computer Science 2025-09-19 Haoyu Tang , Ye Liu , Xi Zhao , Xukai Liu , Yanghai Zhang , Kai Zhang , Xiaofang Zhou , Enhong Chen

The Partial Information Decomposition (PID) framework has emerged as a powerful tool for analyzing high-order interdependencies in complex network systems. However, its application to dynamic processes remains challenging due to the…