BoundingDocs: a Unified Dataset for Document Question Answering with Spatial Annotations

2025-01-06 · Simone Giovannini, Fabio Coppini, Andrea Gemelli, Simone Marinai

We present a unified dataset for document Question-Answering (QA), which is obtained combining several public datasets related to Document AI and visually rich document understanding (VRDU). Our main contribution is twofold: on the one hand we reformulate existing Document AI tasks, such as Information Extraction (IE), into a Question-Answering task, making it a suitable resource for training and evaluating Large Language Models; on the other hand, we release the OCR of all the documents and include the exact position of the answer to be found in the document image as a bounding box. Using this dataset, we explore the impact of different prompting techniques (that might include bounding box information) on the performance of open-weight models, identifying the most effective approaches for document comprehension.

📄 PDF Abstract BibTeX arXiv:2501.03403

Code (0)

등록된 구현이 없습니다.

Tasks

Document AIdocument understandingOptical Character Recognition (OCR)PositionQuestion Answering

SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images

2023-01-12 · Ryota Tanaka, Kyosuke Nishida, Kosuke Nishida, Taku Hasegawa 외

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 docum…

Evidence Selection Question Answering Visual Question Answering Visual Question Answering (VQA)

VDocRAG: Retrieval-Augmented Generation over Visually-Rich Documents

2025-04-14 · CVPR 2025 1 · Ryota Tanaka, Taichi Iki, Taku Hasegawa, Kyosuke Nishida 외

We aim to develop a retrieval-augmented generation (RAG) framework that answers questions over a corpus of visually-rich documents presented in mixed modalities (e.g., charts, tables) and diverse formats (e.g., PDF, PPTX…

Question Answering RAG Retrieval Retrieval-augmented Generation+1

Answering Any-hop Open-domain Questions with Iterative Document Reranking

2020-09-16 · Ping Nie, Yuyu Zhang, Arun Ramamurthy, Le Song

Existing approaches for open-domain question answering (QA) are typically designed for questions that require either single-hop or multi-hop reasoning, which make strong assumptions of the complexity of questions to be a…

Multi-hop Question Answering Natural Questions Open-Domain Question Answering Question Answering+2

CMRAG: Co-modality-based visual document retrieval and question answering

2025-09-02 · Wang Chen, Wenhan Yu, Guanqiang Qi, Weikang Li 외 arxiv

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 l…

Question Answering

AdaDocVQA: Adaptive Framework for Long Document Visual Question Answering in Low-Resource Settings

2025-08-19 · Haoxuan Li, Wei Song, Aofan Liu, Peiwu Qin arxiv

Document Visual Question Answering (Document VQA) faces significant challenges when processing long documents in low-resource environments due to context limitations and insufficient training data. This paper presents Ad…

Visual Question Answering Data Augmentation Text Retrieval