English
Related papers

Related papers: MAVIS: A Benchmark for Multimodal Source Attributi…

200 papers

Retrieval-augmented generation (RAG) is an effective technique that enables large language models (LLMs) to utilize external knowledge sources for generation. However, current RAG systems are solely based on text, rendering it impossible to…

Information Retrieval · Computer Science 2025-03-04 Shi Yu , Chaoyue Tang , Bokai Xu , Junbo Cui , Junhao Ran , Yukun Yan , Zhenghao Liu , Shuo Wang , Xu Han , Zhiyuan Liu , Maosong Sun

Multimodal large language models (MLLMs) can process text presented as images, yet they often perform worse than when the same content is provided as textual tokens. We systematically diagnose this "modality gap" by evaluating seven MLLMs…

Computation and Language · Computer Science 2026-05-26 Kaiser Sun , Xiaochuang Yuan , Hongjun Liu , Chen Zhao , Cheng Zhang , Mark Dredze , Fan Bai

Multimodal Large Language Models (MLLMs) have significantly advanced document understanding, yet current Doc-VQA evaluations score only the final answer and leave the supporting evidence unchecked. This answer-only approach masks a critical…

Computation and Language · Computer Science 2026-05-14 Dongsheng Ma , Jiayu Li , Zhengren Wang , Yijie Wang , Jiahao Kong , Weijun Zeng , Jutao Xiao , Jie Yang , Wentao Zhang , Bin Wang , Conghui He

Retrieval-Augmented Generation (RAG) has become a core paradigm in document question answering tasks. However, existing methods have limitations when dealing with multimodal documents: one category of methods relies on layout analysis and…

Computation and Language · Computer Science 2026-03-09 Wang Chen , Wenhan Yu , Guanqiang Qi , Weikang Li , Yang Li , Lei Sha , Deguo Xia , Jizhou Huang

Social Intelligence Queries (Social-IQ) serve as the primary multimodal benchmark for evaluating a model's social intelligence level. While impressive multiple-choice question(MCQ) accuracy is achieved by current solutions, increasing…

Artificial Intelligence · Computer Science 2025-04-04 Hao Li , Hao Fei , Zechao Hu , Zhengwei Yang , Zheng Wang

Document visual question answering (DocVQA) pipelines that answer questions from documents have broad applications. Existing methods focus on handling single-page documents with multi-modal language models (MLMs), or rely on text-based…

Computer Vision and Pattern Recognition · Computer Science 2024-11-08 Jaemin Cho , Debanjan Mahata , Ozan Irsoy , Yujie He , Mohit Bansal

Multimodal large language models (MLLMs), such as GPT-4o, Gemini, LLaVA, and Flamingo, have made significant progress in integrating visual and textual modalities, excelling in tasks like visual question answering (VQA), image captioning,…

Computer Vision and Pattern Recognition · Computer Science 2024-12-31 Junxiao Xue , Quan Deng , Fei Yu , Yanhao Wang , Jun Wang , Yuehua Li

Large Vision-Language Models (LVLMs) often omit or misrepresent critical visual content in generated image captions. Minimizing such information loss will force LVLMs to focus on image details to generate precise descriptions. However,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Haonan Jia , Shichao Dong , Xin Dong , Zenghui Sun , Jin Wang , Jinsong Lan , Xiaoyong Zhu , Bo Zheng , Kaifu Zhang

Retrieval-augmented Generation (RAG) has demonstrated potential in enhancing medical question-answering systems through the integration of large language models (LLMs) with external medical literature. LLMs can retrieve relevant medical…

Computation and Language · Computer Science 2025-10-29 Mengzhou Sun , Sendong Zhao , Jianyu Chen , Haochun Wang , Bin Qin

Multimodal Large Language Models (MLLMs) perform well in video understanding but degrade on long videos due to fixed-length context and weak long-term dependency modeling. Retrieval-Augmented Generation (RAG) can expand knowledge…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Zhucun Xue , Jiangning Zhang , Xurong Xie , Yuxuan Cai , Yong Liu , Xiangtai Li , Dacheng Tao

Document Visual Question Answering (DocVQA) is a practical yet challenging task, which is to ask questions based on documents while referring to multiple pages and different modalities of information, e.g, images and tables. To handle…

Computer Vision and Pattern Recognition · Computer Science 2025-06-18 Chelsi Jain , Yiran Wu , Yifan Zeng , Jiale Liu , S hengyu Dai , Zhenwen Shao , Qingyun Wu , Huazheng Wang

Understanding the contents of multimodal documents is essential to accurately extract relevant evidence and use it for reasoning. Existing document understanding models tend to generate answers with a single word or phrase directly,…

Information Retrieval · Computer Science 2024-08-15 Jinxu Zhang

Multimodal information extraction (MIE) is crucial for scientific literature, where valuable data is often spread across text, figures, and tables. In materials science, extracting structured information from research articles can…

Computation and Language · Computer Science 2024-10-29 Ghazal Khalighinejad , Sharon Scott , Ollie Liu , Kelly L. Anderson , Rickard Stureborg , Aman Tyagi , Bhuwan Dhingra

Knowledge-based Visual Question Answering (KB-VQA) requires models to answer questions by integrating visual information with external knowledge. However, retrieved knowledge is often noisy, partially irrelevant, or misaligned with the…

Computer Vision and Pattern Recognition · Computer Science 2026-02-19 Xianwei Mao , Kai Ye , Sheng Zhou , Nan Zhang , Haikuan Huang , Bin Li , Jiajun Bu

Retrieval-Augmented Generation (RAG) is an effective approach to enhance the factual accuracy of large language models (LLMs) by retrieving information from external databases, which are typically composed of diverse sources, to supplement…

Machine Learning · Computer Science 2025-10-15 Jeongyeon Hwang , Junyoung Park , Hyejin Park , Dongwoo Kim , Sangdon Park , Jungseul Ok

Retrieval-based multi-image question answering (QA) task involves retrieving multiple question-related images and synthesizing these images to generate an answer. Conventional "retrieve-then-answer" pipelines often suffer from cascading…

Computer Vision and Pattern Recognition · Computer Science 2024-12-20 Peize Li , Qingyi Si , Peng Fu , Zheng Lin , Yan Wang

LLMs can help humans working with long documents, but are known to hallucinate. Attribution can increase trust in LLM responses: The LLM provides evidence that supports its response, which enhances verifiability. Existing approaches to…

Computation and Language · Computer Science 2024-10-24 Jan Buchmann , Xiao Liu , Iryna Gurevych

Recent advancements in Large Vision-Language Models (LVLMs) have significantly enhanced their ability to integrate visual and linguistic information, achieving near-human proficiency in tasks like object recognition, captioning, and visual…

Computer Vision and Pattern Recognition · Computer Science 2025-05-14 Zhikai Wang , Jiashuo Sun , Wenqi Zhang , Zhiqiang Hu , Xin Li , Fan Wang , Deli Zhao

The advancement of large language models (LLMs) has significantly broadened the scope of applications in natural language processing, with multi-modal LLMs extending these capabilities to integrate and interpret visual data. However,…

Computer Vision and Pattern Recognition · Computer Science 2024-06-19 Bingchen Zhao , Yongshuo Zong , Letian Zhang , Timothy Hospedales

Recent advances in Vision-Language Models (VLMs) have achieved impressive progress in multimodal mathematical reasoning. Yet, how much visual information truly contributes to reasoning remains unclear. Existing benchmarks report strong…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Yuandong Wang , Yao Cui , Yuxin Zhao , Zhen Yang , Yangfu Zhu , Zhenzhou Shao