English
Related papers

Related papers: Dual-Space Smoothness for Robust and Balanced LLM …

200 papers

Machine unlearning offers a promising solution to privacy and safety concerns in large language models (LLMs) by selectively removing targeted knowledge while preserving utility. However, current methods are highly sensitive to downstream…

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

Pre-trained language models (PLMs) have consistently demonstrated outstanding performance across a diverse spectrum of natural language processing tasks. Nevertheless, despite their success with unseen data, current PLM-based…

Computation and Language · Computer Science 2024-03-19 Javad Rafiei Asl , Prajwal Panzade , Eduardo Blanco , Daniel Takabi , Zhipeng Cai

The memory challenges associated with training Large Language Models (LLMs) have become a critical concern, particularly when using the Adam optimizer. To address this issue, numerous memory-efficient techniques have been proposed, with…

Machine Learning · Computer Science 2025-02-12 Yiming Chen , Yuan Zhang , Yin Liu , Kun Yuan , Zaiwen Wen

In this paper, we propose Precision-Informed Semantic Modeling (PRISM), a structured topic modeling framework combining the benefits of rich representations captured by LLMs with the low cost and interpretability of latent semantic…

Machine Learning · Computer Science 2026-04-06 Connor Douglas , Utkucan Balci , Joseph Aylett-Bullock

Recently, large language models (LLMs) have emerged as a notable field, attracting significant attention for its ability to automatically generate intelligent contents for various application domains. However, LLMs still suffer from…

Cryptography and Security · Computer Science 2024-04-29 Kongyang Chen , Zixin Wang , Bing Mi , Waixi Liu , Shaowei Wang , Xiaojun Ren , Jiaxing Shen

Jailbreak attacks pose a serious threat to the safety of Large Language Models (LLMs) by crafting adversarial prompts that bypass alignment mechanisms, causing the models to produce harmful, restricted, or biased content. In this paper, we…

Machine Learning · Computer Science 2025-08-22 Xiangman Li , Xiaodong Wu , Qi Li , Jianbing Ni , Rongxing Lu

Reliable evaluation is fundamental to the progress of Large Language Models (LLMs), yet the evaluation process during pre-training is plagued by significant instability that obscures true learning dynamics. In this work, we systematically…

Computation and Language · Computer Science 2026-03-17 Jiapeng Wang , Changxin Tian , Kunlong Chen , Ziqi Liu , Jiaxin Mao , Wayne Xin Zhao , Zhiqiang Zhang , Jun Zhou

Although language models (LMs) demonstrate exceptional capabilities on various tasks, they are potentially vulnerable to extraction attacks, which represent a significant privacy risk. To mitigate the privacy concerns of LMs, machine…

Computation and Language · Computer Science 2024-06-21 Dohyun Lee , Daniel Rim , Minseok Choi , Jaegul Choo

Large language models (LLMs) have achieved impressive capabilities, yet ensuring their safety against harmful prompts remains a critical challenge. Recent work has revealed that the latent representations (embeddings) of harmful and safe…

Computation and Language · Computer Science 2026-03-24 Xu Zhao , Xiting Wang , Weiran Shen

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

In recent years, unlearning techniques, which are methods for inducing a model to "forget" previously learned information, have attracted attention as a way to address privacy and copyright concerns in large language models (LLMs) and large…

Machine Learning · Computer Science 2025-10-29 Tatsuki Kawakami , Kazuki Egashira , Atsuyuki Miyai , Go Irie , Kiyoharu Aizawa

Here, we show that current LLM unlearning methods inherently reduce models' robustness, causing them to misbehave even when a single non-adversarial forget-token is present in the retain-query. Toward understanding underlying causes, we…

Computation and Language · Computer Science 2026-04-21 Dang Huu-Tien , Hoang Thanh-Tung , Anh Bui , Minh-Phuong Nguyen , Le-Minh Nguyen , Naoya Inoue

The imperative to eliminate undesirable data memorization underscores the significance of machine unlearning for large language models (LLMs). Recent research has introduced a series of promising unlearning methods, notably boosting the…

Machine Learning · Computer Science 2025-02-26 Qizhou Wang , Bo Han , Puning Yang , Jianing Zhu , Tongliang Liu , Masashi Sugiyama

While Large Language Models (LLMs) excel at code generation, their inherent tendency toward verbatim memorization of training data introduces critical risks like copyright infringement, insecure emission, and deprecated API utilization,…

Software Engineering · Computer Science 2025-11-25 Xue Jiang , Yihong Dong , Huangzhao Zhang , Tangxinyu Wang , Zheng Fang , Yingwei Ma , Rongyu Cao , Binhua Li , Zhi Jin , Wenpin Jiao , Yongbin Li , Ge Li

Machine unlearning, as a post-hoc processing technique, has gained widespread adoption in addressing challenges like bias mitigation and robustness enhancement, colloquially, machine unlearning for fairness and robustness. However, existing…

Machine Learning · Computer Science 2025-05-27 Xinbao Qiao , Ningning Ding , Yushi Cheng , Meng Zhang

As Spoken Language Models (SLMs) integrate speech and text modalities, they inherit the safety vulnerabilities of their LLM backbone and an expanded attack surface. SLMs have been previously shown to be susceptible to jailbreaking, where…

Machine Learning · Computer Science 2026-03-20 Aravind Krishnan , Karolina Stańczak , Dietrich Klakow

Safety fine-tuning helps align Large Language Models (LLMs) with human preferences for their safe deployment. To better understand the underlying factors that make models safe via safety fine-tuning, we design a synthetic data generation…

Machine Learning · Computer Science 2024-08-22 Samyak Jain , Ekdeep Singh Lubana , Kemal Oksuz , Tom Joy , Philip H. S. Torr , Amartya Sanyal , Puneet K. Dokania

Safety alignment of large language models remains brittle under domain shift and noisy preference supervision. Most existing robust alignment methods focus on uncertainty in alignment data, while overlooking optimization-induced fragility…

Machine Learning · Computer Science 2026-05-22 Yonghui Yang , Wenjian Tao , Jilong Liu , Xingyu Zhu , Junfeng Fang , Weibiao Huang , Le Wu , Richang Hong , Tat-Sent Chua

Language models can retain dangerous knowledge and skills even after extensive safety fine-tuning, posing both misuse and misalignment risks. Recent studies show that even specialized unlearning methods can be easily reversed. To address…

Machine Learning · Computer Science 2025-12-01 Filip Sondej , Yushi Yang , Mikołaj Kniejski , Marcel Windys