English
Related papers

Related papers: Visual Distraction Undermines Moral Reasoning in V…

200 papers

Large language models are increasingly influencing human moral decisions, yet current approaches focus primarily on evaluating rather than actively steering their moral decisions. We formulate this as an out-of-distribution moral alignment…

Artificial Intelligence · Computer Science 2025-11-18 Zhiyu An , Wan Du

The safety alignment ability of Vision-Language Models (VLMs) is prone to be degraded by the integration of the vision module compared to its LLM backbone. We investigate this phenomenon, dubbed as ''safety alignment degradation'' in this…

Computation and Language · Computer Science 2024-10-14 Qin Liu , Chao Shang , Ling Liu , Nikolaos Pappas , Jie Ma , Neha Anna John , Srikanth Doss , Lluis Marquez , Miguel Ballesteros , Yassine Benajiba

Recent studies reveal that integrating new modalities into Large Language Models (LLMs), such as Vision-Language Models (VLMs), creates a new attack surface that bypasses existing safety training techniques like Supervised Fine-tuning (SFT)…

Computation and Language · Computer Science 2025-10-15 Trishna Chakraborty , Erfan Shayegani , Zikui Cai , Nael Abu-Ghazaleh , M. Salman Asif , Yue Dong , Amit K. Roy-Chowdhury , Chengyu Song

Multi-modal large language models (MLLMs) are trained based on large language models (LLM), with an enhanced capability to comprehend multi-modal inputs and generate textual responses. While they excel in multi-modal tasks, the pure NLP…

Computation and Language · Computer Science 2023-09-14 Haoqin Tu , Bingchen Zhao , Chen Wei , Cihang Xie

Autonomous Driving System (ADS) testing plays a crucial role in their development, with the current focus primarily on functional and safety testing. However, evaluating the non-functional morality of ADSs, particularly their…

Software Engineering · Computer Science 2025-05-07 Wenbing Tang , Mingfei Cheng , Yuan Zhou , Yang Liu

Multimodal large language models (MLLMs) face safety misalignment, where visual inputs enable harmful outputs. To address this, existing methods require explicit safety labels or contrastive data; yet, threat-related concepts are concrete…

Computer Vision and Pattern Recognition · Computer Science 2026-04-16 Qishun Yang , Shu Yang , Lijie Hu , Di Wang

Multimodal large reasoning models (MLRMs) are increasingly deployed for vision-language tasks that produce explicit intermediate rationales. However, reasoning traces can contain unsafe content even when the final answer is non-harmful,…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Yuxiao Xiang , Junchi Chen , Zhenchao Jin , Changtao Miao , Haojie Yuan , Qi Chu , Tao Gong , Nenghai Yu

Vision-Language Models (VLMs) are increasingly deployed in autonomous driving and embodied AI systems, where reliable perception is critical for safe semantic reasoning and decision-making. While recent VLMs demonstrate strong performance…

Computer Vision and Pattern Recognition · Computer Science 2026-01-16 Guo Cheng

Visual reasoning is a core component of human intelligence and a critical capability for advanced multimodal models. Yet current reasoning evaluations of multimodal large language models (MLLMs) often rely on text descriptions and allow…

Computer Vision and Pattern Recognition · Computer Science 2025-04-22 Weiye Xu , Jiahao Wang , Weiyun Wang , Zhe Chen , Wengang Zhou , Aijun Yang , Lewei Lu , Houqiang Li , Xiaohua Wang , Xizhou Zhu , Wenhai Wang , Jifeng Dai , Jinguo Zhu

The various limitations of Generative AI, such as hallucinations and model failures, have made it crucial to understand the role of different modalities in Visual Language Model (VLM) predictions. Our work investigates how the integration…

Artificial Intelligence · Computer Science 2024-10-03 Kenza Amara , Lukas Klein , Carsten Lüth , Paul Jäger , Hendrik Strobelt , Mennatallah El-Assady

Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated impressive performance on standard visual reasoning benchmarks. However, there is growing concern that these models rely excessively on linguistic shortcuts…

Computation and Language · Computer Science 2026-01-09 Ziteng Wang , Yujie He , Guanliang Li , Siqi Yang , Jiaqi Xiong , Songxiang Liu

Even modern AI models often remain vulnerable to multimodal queries in which harmful intent is embedded in images. A widely used approach for safety alignment is training with extensive multimodal safety datasets, but the costs of data…

Computer Vision and Pattern Recognition · Computer Science 2026-03-30 Jonghyun Park , Minhyuk Seo , Chaewon Yeo , Jonghyun Choi

Recent research has increasingly focused on multimodal mathematical reasoning, particularly emphasizing the creation of relevant datasets and benchmarks. Despite this, the role of visual information in reasoning has been underexplored. Our…

Computer Vision and Pattern Recognition · Computer Science 2025-06-05 Yufang Liu , Yao Du , Tao Ji , Jianing Wang , Yang Liu , Yuanbin Wu , Aimin Zhou , Mengdi Zhang , Xunliang Cai

Large Language Models (LLMs) are increasingly deployed in multilingual and multicultural environments where moral reasoning is essential for generating ethically appropriate responses. Yet, the dominant pretraining of LLMs on…

Computation and Language · Computer Science 2025-09-29 Sualeha Farid , Jayden Lin , Zean Chen , Shivani Kumar , David Jurgens

Vision language models (VLMs) extend the reasoning capabilities of large language models (LLMs) to cross-modal settings, yet remain highly vulnerable to multimodal jailbreak attacks. Existing defenses predominantly rely on safety…

Artificial Intelligence · Computer Science 2026-04-14 Mengxuan Wang , Yuxin Chen , Gang Xu , Tao He , Hongjie Jiang , Ming Li

Vision-Language Models (VLMs) have been shown to be blind, often underutilizing their visual inputs even on tasks that require visual reasoning. In this work, we demonstrate that VLMs are selectively blind. They modulate the amount of…

Computer Vision and Pattern Recognition · Computer Science 2026-03-23 Wan-Cyuan Fan , Jiayun Luo , Declan Kutscher , Leonid Sigal , Ritwik Gupta

Recent advances in embodied Vision-Language Agentic Systems (VLAS), powered by large vision-language models (LVLMs), enable AI systems to perceive and reason over real-world scenes. Within this context, environmental signals such as traffic…

Computer Vision and Pattern Recognition · Computer Science 2026-04-23 Jiamin Chang , Minhui Xue , Ruoxi Sun , Shuchao Pang , Salil S. Kanhere , Hammond Pearce

Vision-Language Models (VLMs) have recently demonstrated incredible strides on diverse vision language tasks. We dig into vision-based deductive reasoning, a more sophisticated but less explored realm, and find previously unexposed…

Artificial Intelligence · Computer Science 2024-10-02 Yizhe Zhang , He Bai , Ruixiang Zhang , Jiatao Gu , Shuangfei Zhai , Josh Susskind , Navdeep Jaitly

Vision-Language Models (VLMs) have achieved substantial progress across a wide range of understanding and reasoning tasks, driven by large-scale image-text training aimed at multimodal fusion. Ideally, replacing a textual question with its…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Feng Han , Zhixiong Zhang , Zheming Liang , Yibin Wang , Jiaqi Wang

The increasing integration of Visual Language Models (VLMs) into AI systems necessitates robust model alignment, especially when handling multimodal content that combines text and images. Existing evaluation datasets heavily lean towards…

Computation and Language · Computer Science 2026-03-05 Gabriel Downer , Sean Craven , Damian Ruck , Jake Thomas