English
Related papers

Related papers: Doc2SoarGraph: Discrete Reasoning over Visually-Ri…

200 papers

With the development of deep learning techniques and large scale datasets, the question answering (QA) systems have been quickly improved, providing more accurate and satisfying answers. However, current QA systems either focus on the…

Computation and Language · Computer Science 2021-01-19 Bingning Wang , Ting Yao , Weipeng Chen , Jingfang Xu , Xiaochuan Wang

Current general-purpose large language models (LLMs) commonly exhibit knowledge hallucination and insufficient domain-specific adaptability in domain-specific tasks, limiting their effectiveness in specialized question answering scenarios.…

Information Retrieval · Computer Science 2025-09-16 Mengzheng Yang , Yanfei Ren , David Osei Opoku , Ruochang Li , Peng Ren , Chunxiao Xing

Object detection in documents is a key step to automate the structural elements identification process in a digital or scanned document through understanding the hierarchical structure and relationships between different elements. Large and…

Computer Vision and Pattern Recognition · Computer Science 2024-02-21 Ayan Banerjee , Sanket Biswas , Josep Lladós , Umapada Pal

Scientific documents contain complex multimodal structures, which makes evidence localization and scientific reasoning in Document Visual Question Answering particularly challenging. However, most existing benchmarks evaluate models only at…

Databases · Computer Science 2026-03-31 Wenhan Yu , Zhaoxi Zhang , Wang Chen , Guanqiang Qi , Weikang Li , Lei Sha , Deguo Xia , Jizhou Huang

Visual question answering on document images that contain textual, visual, and layout information, called document VQA, has received much attention recently. Although many datasets have been proposed for developing document VQA systems,…

Computation and Language · Computer Science 2023-01-13 Ryota Tanaka , Kyosuke Nishida , Kosuke Nishida , Taku Hasegawa , Itsumi Saito , Kuniko Saito

The conventional use of the Retrieval-Augmented Generation (RAG) architecture has proven effective for retrieving information from diverse documents. However, challenges arise in handling complex table queries, especially within PDF…

Machine Learning · Computer Science 2024-02-13 Uday Allu , Biddwan Ahmed , Vishesh Tripathi

Question-answering (QA) on hybrid scientific tabular and textual data deals with scientific information, and relies on complex numerical reasoning. In recent years, while tabular QA has seen rapid progress, understanding their robustness on…

Computation and Language · Computer Science 2024-04-02 Akash Ghosh , B Venkata Sahith , Niloy Ganguly , Pawan Goyal , Mayank Singh

Document Visual Question Answering (DocVQA) remains challenging for existing Vision-Language Models (VLMs), especially under complex reasoning and multi-step workflows. Current approaches struggle to decompose intricate questions into…

Computer Vision and Pattern Recognition · Computer Science 2026-03-04 Aymen Lassoued , Mohamed Ali Souibgui , Yousri Kessentini

Medical image segmentation driven by free-text clinical instructions is a critical frontier in computer-aided diagnosis. However, existing multimodal and foundation models struggle with the semantic ambiguity of clinical reports and fail to…

Computer Vision and Pattern Recognition · Computer Science 2026-04-08 Chenyu Xue , Yiran Liu , Mian Zhou , Jionglong Su , Zhixiang Lu

Understanding complex multimodal documents remains challenging due to their structural inconsistencies and limited training data availability. We introduce \textit{DocsRay}, a training-free document understanding system that integrates…

Machine Learning · Computer Science 2025-08-01 Hyeon Seong Jeong , Sangwoo Jo , Byeong Hyun Yoon , Yoonseok Heo , Haedong Jeong , Taehoon Kim

Document images encapsulate a wealth of knowledge, while the portability of spoken queries enables broader and flexible application scenarios. Yet, no prior work has explored knowledge base question answering over visual document images…

Computer Vision and Pattern Recognition · Computer Science 2025-09-11 Peijin Xie , Shun Qian , Bingquan Liu , Dexin Wang , Lin Sun , Xiangzheng Zhang

Since many real-world documents combine textual and tabular data, robust Retrieval Augmented Generation (RAG) systems are essential for effectively accessing and analyzing such content to support complex reasoning tasks. Therefore, this…

Information Retrieval · Computer Science 2026-01-19 Jan Strich , Enes Kutay Isgorur , Maximilian Trescher , Chris Biemann , Martin Semmann

Numerical reasoning over hybrid data containing both textual and tabular content (e.g., financial reports) has recently attracted much attention in the NLP community. However, existing question answering (QA) benchmarks over hybrid data…

Artificial Intelligence · Computer Science 2022-06-06 Yilun Zhao , Yunxiang Li , Chenying Li , Rui Zhang

The sheer volume of financial statements makes it difficult for humans to access and analyze a business's financials. Robust numerical reasoning likewise faces unique challenges in this domain. In this work, we focus on answering deep…

Diagram question answering (Diagram QA) requires reasoning-level attribution that links each question-answer pair to all visual regions needed to derive the answer, rather than only the region containing the final response. Creating such…

Visual Question Answering (VQA) attracts much attention from both industry and academia. As a multi-modality task, it is challenging since it requires not only visual and textual understanding, but also the ability to align cross-modality…

Computer Vision and Pattern Recognition · Computer Science 2022-01-27 Peixi Xiong , Quanzeng You , Pei Yu , Zicheng Liu , Ying Wu

The rapid progress of generative AI has enabled increasingly realistic text-centric image forgeries, posing major challenges to document safety. Existing forensic methods mainly rely on visual cues and lack evidence-based reasoning to…

Computer Vision and Pattern Recognition · Computer Science 2026-04-06 Fanwei Zeng , Changtao Miao , Jing Huang , Zhiya Tan , Shutao Gong , Xiaoming Yu , Yang Wang , Weibin Yao , Joey Tianyi Zhou , Jianshu Li , Yin Yan

In enterprise datasets, documents are rarely pure. They are not just text, nor just numbers; they are a complex amalgam of narrative and structure. Current Retrieval-Augmented Generation (RAG) systems have attempted to address this…

Artificial Intelligence · Computer Science 2026-01-16 Alex Dantart , Marco Kóvacs-Navarro

Question answering over visually rich documents (VRDs) requires reasoning not only over isolated content but also over documents' structural organization and cross-page dependencies. However, conventional retrieval-augmented generation…

Computation and Language · Computer Science 2026-03-03 Zhivar Sourati , Zheng Wang , Marianne Menglin Liu , Yazhe Hu , Mengqing Guo , Sujeeth Bharadwaj , Kyu Han , Tao Sheng , Sujith Ravi , Morteza Dehghani , Dan Roth

Question Answering over Temporal Knowledge Graphs (TKGQA) has attracted growing interest for handling time-sensitive queries. However, existing methods still struggle with: 1) weak incorporation of temporal constraints in question…

Computation and Language · Computer Science 2026-02-24 Wuzhenghong Wen , Bowen Zhou , Jinwen Huang , Xianjie Wu , Yuwei Sun , Su Pan , Liang Li , Jianting Liu