English
Related papers

Related papers: Layered Unlearning for Adversarial Relearning

200 papers

Despite significant progress in safety alignment, large language models (LLMs) remain susceptible to jailbreak attacks. Existing defense mechanisms have not fully deleted harmful knowledge in LLMs, which allows such attacks to bypass…

Computation and Language · Computer Science 2025-05-27 Zesheng Shi , Yucheng Zhou , Jing Li

Machine unlearning aims to remove sensitive or undesired data from large language models. However, recent studies suggest that unlearning is often shallow, claiming that removed knowledge can easily be recovered. In this work, we critically…

Machine Learning · Computer Science 2025-06-03 Zhili Feng , Yixuan Even Xu , Alexander Robey , Robert Kirk , Xander Davies , Yarin Gal , Avi Schwarzschild , J. Zico Kolter

Machine unlearning, the study of efficiently removing the impact of specific training instances on a model, has garnered increased attention in recent years due to regulatory guidelines such as the \emph{Right to be Forgotten}. Achieving…

Machine Learning · Computer Science 2024-06-07 Martin Pawelczyk , Seth Neel , Himabindu Lakkaraju

Post-training pruning is an effective approach for reducing the size and inference cost of large language models (LLMs), but existing methods often face a trade-off between pruning quality and computational efficiency. Heuristic pruning…

Computation and Language · Computer Science 2026-02-10 Peiqi Yu , Jinhao Wang , Xinyi Sui , Nam Ling , Wei Wang , Wei Jiang

Recent advances in large reasoning models (LRMs) have enabled strong chain-of-thought (CoT) generation through test-time computation. While these multi-step reasoning capabilities represent a major milestone in language model performance,…

Artificial Intelligence · Computer Science 2025-10-14 Changsheng Wang , Chongyu Fan , Yihua Zhang , Jinghan Jia , Dennis Wei , Parikshit Ram , Nathalie Baracaldo , Sijia Liu

Large Language Models (LLMs) are known to be vulnerable to jailbreak attacks. An important observation is that, while different types of jailbreak attacks can generate significantly different queries, they mostly result in similar responses…

Cryptography and Security · Computer Science 2025-05-21 Zhexin Zhang , Junxiao Yang , Yida Lu , Pei Ke , Shiyao Cui , Chujie Zheng , Hongning Wang , Minlie Huang

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

Machine unlearning considers the removal of the contribution of a set of data points from a trained model. In a distributed setting, where a server orchestrates training using data available at a set of remote users, unlearning is essential…

Signal Processing · Electrical Eng. & Systems 2025-05-07 Natalie Lang , Alon Helvitz , Nir Shlezinger

As the post-training of large language models (LLMs) advances from instruction-following to complex reasoning tasks, understanding how different data affect finetuning dynamics remains largely unexplored. In this paper, we present a…

Machine Learning · Computer Science 2026-05-12 Ming Li , Yanhong Li , Ziyue Li , Tianyi Zhou

Machine unlearning aims to remove specific information, e.g. sensitive or undesirable content, from large language models (LLMs) while preserving overall performance. We propose an inference-time unlearning algorithm that uses contrastive…

Computation and Language · Computer Science 2025-06-17 Vinith M. Suriyakumar , Ayush Sekhari , Ashia Wilson

As a new and promising approach, existing machine unlearning (MU) works typically emphasize theoretical formulations or optimization objectives to achieve knowledge removal. However, when deployed in real-world scenarios, such solutions…

Machine Learning · Computer Science 2025-10-31 Minyi Peng , Darian Gunamardi , Ivan Tjuawinata , Kwok-Yan Lam

Post-training has demonstrated its importance in enhancing the reasoning capabilities of large language models (LLMs). The primary post-training methods can be categorized into supervised fine-tuning (SFT) and reinforcement fine-tuning…

Machine Learning · Computer Science 2025-10-21 Mingyang Liu , Gabriele Farina , Asuman Ozdaglar

Despite the empirical success of using Adversarial Training to defend deep learning models against adversarial perturbations, so far, it still remains rather unclear what the principles are behind the existence of adversarial perturbations,…

Machine Learning · Computer Science 2022-06-14 Zeyuan Allen-Zhu , Yuanzhi Li

The rapid development in the performance of large language models (LLMs) is accompanied by the escalation of model size, leading to the increasing cost of model training and inference. Previous research has discovered that certain layers in…

Computation and Language · Computer Science 2024-10-14 Fangwei Zhu , Dian Li , Jiajun Huang , Gang Liu , Hui Wang , Zhifang Sui

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

Large Language Models (LLMs) often produce plausible but poorly-calibrated answers, limiting their reliability on reasoning-intensive tasks. We present Reinforcement Learning from Self-Feedback (RLSF), a post-training stage that uses the…

Computation and Language · Computer Science 2025-07-30 Carel van Niekerk , Renato Vukovic , Benjamin Matthias Ruppik , Hsien-chin Lin , Milica Gašić

Large language models (LLMs) serve as giant information stores, often including personal or copyrighted data, and retraining them from scratch is not a viable option. This has led to the development of various fast, approximate unlearning…

Computation and Language · Computer Science 2024-10-18 Minseok Choi , ChaeHun Park , Dohyun Lee , Jaegul Choo

Pretrained language models memorize vast amounts of information, including private and copyrighted data, raising significant safety concerns. Retraining these models after excluding sensitive data is prohibitively expensive, making machine…

Computation and Language · Computer Science 2024-10-04 Minseok Choi , Kyunghyun Min , Jaegul Choo

Large Language Models (LLMs) are increasingly integrated into real-world applications, raising concerns about privacy, security and the need to remove undesirable knowledge. Machine Unlearning has emerged as a promising solution, yet faces…

Machine Learning · Computer Science 2025-10-22 Yisheng Zhong , Zhengbang Yang , Zhuangdi Zhu

In the rapid advancement of artificial intelligence, privacy protection has become crucial, giving rise to machine unlearning. Machine unlearning is a technique that removes specific data influences from trained models without the need for…

Machine Learning · Computer Science 2025-06-23 Wenhan Chang , Tianqing Zhu , Ping Xiong , Yufeng Wu , Faqian Guan , Wanlei Zhou
‹ Prev 1 4 5 6 7 8 10 Next ›