English
Related papers

Related papers: Cross-Modal Safety Alignment: Is textual unlearnin…

200 papers

Vision-Language Models (VLMs) have achieved remarkable progress in multimodal reasoning tasks through enhanced chain-of-thought capabilities. However, this advancement also introduces novel safety risks, as these models become increasingly…

Computer Vision and Pattern Recognition · Computer Science 2025-10-22 Yinan Xia , Yilei Jiang , Yingshui Tan , Xiaoyong Zhu , Xiangyu Yue , Bo Zheng

Multimodal large language models (MLLMs) may memorize sensitive cross-modal information during pretraining, making machine unlearning (MU) crucial. Existing methods typically evaluate unlearning effectiveness based on output deviations,…

Computation and Language · Computer Science 2026-05-18 Jiahui Guang , Yingjie Zhu , Cuiyun Gao , Haiyan Wang , Jing Li , Di Shao , Zhaoquan Gu

Large language models (LLMs) learn undesirable properties during pretraining, including dangerous knowledge and toxic text generation. Just as post-training uses different objectives to shape different behaviors, we argue that unlearning…

Computation and Language · Computer Science 2026-05-27 Berk Atil , Vipul Gupta , Rebecca J. Passonneau

With the rapid development of large language models (LLMs), they are not only used as general-purpose AI assistants but are also customized through further fine-tuning to meet the requirements of different applications. A pivotal factor in…

Computation and Language · Computer Science 2024-01-23 Pengyu Wang , Dong Zhang , Linyang Li , Chenkun Tan , Xinghao Wang , Ke Ren , Botian Jiang , Xipeng Qiu

Rapid advancements in Visual Language Models (VLMs) have transformed multimodal understanding but are often constrained by generating English responses regardless of the input language. This phenomenon has been termed as Image-induced…

Computer Vision and Pattern Recognition · Computer Science 2025-05-21 Iñigo Pikabea , Iñaki Lacunza , Oriol Pareras , Carlos Escolano , Aitor Gonzalez-Agirre , Javier Hernando , Marta Villegas

Generalizable alignment is a core challenge for deploying Large Language Models (LLMs) safely in real-world NLP applications. Current alignment methods, including Reinforcement Learning from Human Feedback (RLHF), often fail to guarantee…

Computation and Language · Computer Science 2025-04-07 Jaymari Chua , Chen Wang , Lina Yao

Large language models (LLMs) have demonstrated that large-scale pretraining enables systems to adapt rapidly to new problems with little supervision in the language domain. This success, however, has not translated as effectively to the…

Computer Vision and Pattern Recognition · Computer Science 2025-11-04 Pablo Acuaviva , Aram Davtyan , Mariam Hassan , Sebastian Stapf , Ahmad Rahimi , Alexandre Alahi , Paolo Favaro

Multimodal large language models (MLLMs) achieve strong performance by jointly processing inputs from multiple modalities, such as vision, audio, and language. However, building such models or extending them to new modalities often requires…

Machine Learning · Computer Science 2026-03-24 Md Kaykobad Reza , Ameya Patil , Edward Ayrapetian , M. Salman Asif

Large-scale pre-trained Vision-Language Models (VLMs) have significantly advanced transfer learning across diverse tasks. However, adapting these models with limited few-shot data often leads to overfitting, undermining their ability to…

Computer Vision and Pattern Recognition · Computer Science 2025-05-16 Yuncheng Guo , Xiaodong Gu

Large Language Models (LLMs) are increasingly integrated into educational applications. However, they remain vulnerable to jailbreak and fine-tuning attacks, which can compromise safety alignment and lead to harmful outputs. Existing…

Computation and Language · Computer Science 2025-11-19 Xin Yi , Yue Li , Dongsheng Shi , Linlin Wang , Xiaoling Wang , Liang He

The current safeguard mechanisms for large language models (LLMs) are indeed susceptible to jailbreak attacks, making them inherently fragile. Even the process of fine-tuning on apparently benign data for downstream tasks can jeopardize…

Computation and Language · Computer Science 2024-05-16 Xin Yi , Shunfan Zheng , Linlin Wang , Xiaoling Wang , Liang He

Vision-language models (VLMs) often inherit the biases and unsafe associations present within their large-scale training dataset. While recent approaches mitigate unsafe behaviors, their evaluation focuses on how safe the model is on unsafe…

Computer Vision and Pattern Recognition · Computer Science 2026-01-13 Moreno D'Incà , Elia Peruzzo , Xingqian Xu , Humphrey Shi , Nicu Sebe , Massimiliano Mancini

Vision-language models (VLMs) are increasingly applied to identify unsafe or inappropriate images due to their internal ethical standards and powerful reasoning abilities. However, it is still unclear whether they can recognize various…

Cryptography and Security · Computer Science 2025-07-16 Yiting Qu , Michael Backes , Yang Zhang

Large Language Models (LLMs) have been adopted and deployed worldwide for a broad variety of applications. However, ensuring their safe use remains a significant challenge. Preference training and safety measures often overfit to harms…

Computation and Language · Computer Science 2024-10-15 Aakanksha , Arash Ahmadian , Seraphina Goldfarb-Tarrant , Beyza Ermis , Marzieh Fadaee , Sara Hooker

As vision-language models (VLMs) become increasingly capable, maintaining a balance between safety and usefulness remains a central challenge. Safety mechanisms, while essential, can backfire, causing over-refusal, where models decline…

Computation and Language · Computer Science 2026-03-20 Kaixuan Ren , Preslav Nakov , Usman Naseem

The integration of visual and textual data in Vision-Language Pre-training (VLP) models is crucial for enhancing vision-language understanding. However, the adversarial robustness of these models, especially in the alignment of image-text…

Multimedia · Computer Science 2025-06-03 Youze Wang , Wenbo Hu , Yinpeng Dong , Hanwang Zhang , Hang Su , Richang Hong

Vision Language Models (VLMs) are designed to extend Large Language Models (LLMs) with visual capabilities, yet in this work we observe a surprising phenomenon: VLMs can outperform their underlying LLMs on purely text-only tasks,…

Machine Learning · Computer Science 2026-02-18 Nicolas Buzeta , Felipe del Rio , Cristian Hinostroza , Denis Parra , Hans Lobel , Rodrigo Toro Icarte

The advent of Large Language Models (LLMs) has significantly reshaped the trajectory of the AI revolution. Nevertheless, these LLMs exhibit a notable limitation, as they are primarily adept at processing textual information. To address this…

Computer Vision and Pattern Recognition · Computer Science 2025-10-15 Akash Ghosh , Arkadeep Acharya , Sriparna Saha , Vinija Jain , Aman Chadha

Vision-language models (VLMs) allow to embed texts and images in a shared representation space. However, it has been shown that these models are subject to a modality gap phenomenon meaning there exists a clear separation between the…

Computer Vision and Pattern Recognition · Computer Science 2025-05-07 François Role , Sébastien Meyer , Victor Amblard

The rapid advancement of Multimodal Large Language Models (MLLMs) has introduced complex security challenges, particularly at the intersection of textual and visual safety. While existing schemes have explored the security vulnerabilities…

Computer Vision and Pattern Recognition · Computer Science 2026-01-23 Mingyu Yu , Lana Liu , Zhehao Zhao , Wei Wang , Sujuan Qin
‹ Prev 1 3 4 5 6 7 10 Next ›