English
Related papers

Related papers: Soft Token Attacks Cannot Reliably Audit Unlearnin…

200 papers

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

Large language model unlearning has garnered increasing attention due to its potential to address security and privacy concerns, leading to extensive research in the field. However, much of this research has concentrated on instance-level…

Computation and Language · Computer Science 2025-05-20 Weitao Ma , Xiaocheng Feng , Weihong Zhong , Lei Huang , Yangfan Ye , Xiachong Feng , Bing Qin

Large Language Models (LLMs) face significant challenges in maintaining privacy, ethics, and compliance, when sensitive or obsolete data must be selectively removed. Retraining these models from scratch is computationally infeasible,…

Computation and Language · Computer Science 2025-03-10 Dinesh Srivasthav P , Bala Mallikarjunarao Garlapati

Large language models (LLMs) are vulnerable when trained on datasets containing harmful content, which leads to potential jailbreaking attacks in two scenarios: the integration of harmful texts within crowdsourced data used for pre-training…

Cryptography and Security · Computer Science 2024-06-03 Xiaoqun Liu , Jiacheng Liang , Muchao Ye , Zhaohan Xi

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

Unlearning in Large Language Models (LLMs) aims to enhance safety, mitigate biases, and comply with legal mandates, such as the right to be forgotten. However, existing unlearning methods are brittle: minor query modifications, such as…

Artificial Intelligence · Computer Science 2026-03-13 Raj Sanjay Shah , Jing Huang , Keerthiram Murugesan , Nathalie Baracaldo , Diyi Yang

Large language models (LLMs) are vulnerable to jailbreak attacks - resulting in harmful, unethical, or biased text generations. However, existing jailbreaking methods are computationally costly. In this paper, we propose the weak-to-strong…

Computation and Language · Computer Science 2025-07-25 Xuandong Zhao , Xianjun Yang , Tianyu Pang , Chao Du , Lei Li , Yu-Xiang Wang , William Yang Wang

Despite efforts to align large language models (LLMs) with human intentions, widely-used LLMs such as GPT, Llama, and Claude are susceptible to jailbreaking attacks, wherein an adversary fools a targeted LLM into generating objectionable…

Machine Learning · Computer Science 2024-06-17 Alexander Robey , Eric Wong , Hamed Hassani , George J. Pappas

Machine unlearning, a novel area within artificial intelligence, focuses on addressing the challenge of selectively forgetting or reducing undesirable knowledge or behaviors in machine learning models, particularly in the context of large…

Computation and Language · Computer Science 2024-05-27 Saaketh Koundinya Gundavarapu , Shreya Agarwal , Arushi Arora , Chandana Thimmalapura Jagadeeshaiah

Large Language Models (LLMs) are trained with safety alignment to prevent generating malicious content. Although some attacks have highlighted vulnerabilities in these safety-aligned LLMs, they typically have limitations, such as…

Machine Learning · Computer Science 2026-03-11 Jesson Wang , Zhanhao Hu , David Wagner

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

This paper investigates the propagation of harmful information in multilingual large language models (LLMs) and evaluates the efficacy of various unlearning methods. We demonstrate that fake information, regardless of the language it is in,…

Computation and Language · Computer Science 2025-09-04 Taiming Lu , Philipp Koehn

The pre-training of large language models (LLMs) relies on massive text datasets sourced from diverse and difficult-to-curate origins. Although membership inference attacks and hidden canaries have been explored to trace data usage, such…

Cryptography and Security · Computer Science 2025-06-19 Wassim Bouaziz , Mathurin Videau , Nicolas Usunier , El-Mahdi El-Mhamdi

This study investigates the concept of the `right to be forgotten' within the context of large language models (LLMs). We explore machine unlearning as a pivotal solution, with a focus on pre-trained models--a notably under-researched area.…

Computation and Language · Computer Science 2024-05-31 Jin Yao , Eli Chien , Minxin Du , Xinyao Niu , Tianhao Wang , Zezhou Cheng , Xiang Yue

Large language Model (LLM) unlearning, i.e., selectively removing information from LLMs, is vital for responsible model deployment. Differently, LLM knowledge editing aims to modify LLM knowledge instead of removing it. Though editing and…

Machine Learning · Computer Science 2025-05-27 Zexi Li , Xiangzhu Wang , William F. Shen , Meghdad Kurmanji , Xinchi Qiu , Dongqi Cai , Chao Wu , Nicholas D. Lane

Student simulation can support learning-by-teaching pedagogy where human students (as tutors) teach AI-simulated novice students (as tutees). Recent research often relies on prompt engineering with large language models (LLMs) to simulate…

Human-Computer Interaction · Computer Science 2026-03-31 Jiajia Song , Zhihan Guo , Jionghao Lin

Large language models are pre-trained on uncurated text datasets consisting of trillions of tokens scraped from the Web. Prior work has shown that: (1) web-scraped pre-training datasets can be practically poisoned by malicious actors; and…

Cryptography and Security · Computer Science 2024-10-18 Yiming Zhang , Javier Rando , Ivan Evtimov , Jianfeng Chi , Eric Michael Smith , Nicholas Carlini , Florian Tramèr , Daphne Ippolito

In this paper, we present a challenging code reasoning task: vulnerability detection. Large Language Models (LLMs) have shown promising results in natural-language and math reasoning, but state-of-the-art (SOTA) models reported only 54.5%…

Software Engineering · Computer Science 2025-01-09 Benjamin Steenhoek , Md Mahbubur Rahman , Monoshi Kumar Roy , Mirza Sanjida Alam , Hengbo Tong , Swarna Das , Earl T. Barr , Wei Le

The security of biomedical Multimodal Large Language Models (MLLMs) has attracted increasing attention. However, training samples easily contain private information and incorrect knowledge that are difficult to detect, potentially leading…

Computer Vision and Pattern Recognition · Computer Science 2025-08-07 Dunyuan Xu , Xikai Yang , Yaoqian Li , Jinpeng Li , Pheng-Ann Heng

Machine unlearning has the potential to improve the safety of large language models (LLMs) by removing sensitive or harmful information post hoc. A key challenge in unlearning involves balancing between forget quality (effectively…

Machine Learning · Computer Science 2025-06-23 Shengyuan Hu , Neil Kale , Pratiksha Thaker , Yiwei Fu , Steven Wu , Virginia Smith
‹ Prev 1 3 4 5 6 7 10 Next ›