Long-Document VQA

VQA: Visual Question Answering

Follow this topic Ask about this topic

Latest papers

17 papers2 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

One Fact, Many Places: Redundant Evidence in Long Visual Documents Breaks Single-Gold Evaluation of Retrieval, Citation and Attribution
Oct 19, 2026Xiaokang Yuan, Binhui Yao, Luwei Yang +2IR Evaluation Evidence Retrieval
Zhejiang University, Hangzhou, China · Zhejiang Geely Holding Group Co., Ltd, Hangzhou, China
VELD-QA: A Large-Scale Dataset for Visual Evidence Grounding and Question Answering in Long Documents
Oct 14, 2026Zhivar Sourati, Marianne Menglin Liu, Rongguang Wang +12Long-Document VQA Document QA
University of Southern California · Oracle AI · Turing Enterprise Inc +1
An Empirical Study of VLM Pipelines for Long-Document QA
Sep 24, 2026Kenan E. Ak, Jay Mohta, Gwang Gook Lee +2VLM Evaluation Tool Use in VLMs
Capability-Routed Visual Retrieval and Evidence Threading for Long-Context Document Question Answering
Sep 7, 2026Amirul Rahman, Aisha Karim, Kenji Nakamura +1Document QA Long-Document VQA
University of Malaya
AWM: Answerable Working Memory for Long-Document VQA Agents
Aug 26, 2026Dongzhuoran Zhou, Yuqicheng Zhu, Yule Liu +5Long-Document VQA Long-Context QA
University of Oslo · Bosch Center for AI · University of Stuttgart +2
What the Reranker Sees: Multi-Aspect Page Annotation for Long-Document Multimodal Question Answering
Aug 14, 2026Guanchen Wu, Jiayuan Ding, Subhabrata Mukherjee +1Long-Document VQA Multimodal QA
Department of Computer Science, Emory University, Atlanta, GA, USA · Hippocratic AI, Palo Alto, CA, USA
InSight-doc: Agentic Visual Perception for Long-Document Understanding
Aug 11, 2026Kaican Li, Weiyan Xie, Lewei Yao +4Document Understanding Visual Question Answering
1The Hong Kong University of Science and Technology · 2Huawei
DocTrace: Towards Traceable Long Document VQA via Hierarchical Evidence Graph Reasoning
Aug 4, 2026Le Xiang, Zhicheng Guan, Hong Chen +5Visual Question Answering Long-Document VQA
Baidu Basic Model Research and Development Department, Baidu Inc. · Tsinghua Shenzhen International Graduate School, Tsinghua University
HierDoc: Hierarchical Page-to-Region Evidence Routing for Long-Document Visual Question Answering
Jul 31, 2026Rongjian Gu, Wengang Zhou, Junyu Xiong +4Visual Question Answering Long-Document VQA
University of Science and Technology of China · 2iFLYTEK Research · 3Anhui Transport Consulting & Design Institute Co. Ltd., Hefei, China
VinQA: Visual Elements Interleaved Long-form Answer Generation for Real-World Multimodal Document QA
Jun 15, 2026Young Rok Jang, Hyesoo Kong, Kyunghwan An +3Multimodal QA Multimodal Understanding
LG AI Research
Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context
May 13, 2026Zhaowei Wang, Lishu Luo, Haodong Duan +9Visual Question Answering Vision-Language Models
CSE Department, HKUST · ByteDance Seed
DocScope: Benchmarking Verifiable Reasoning for Trustworthy Long-Document Understanding
May 9, 2026Xiang Feng, Jiawei Zhou, Zhangfeng Huang +6Multimodal Understanding LLM Answer Verification
School of Computer Science, National Engineering Research Center for Multimedia Software and Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, China · Alibaba Group, Hangzhou, China · Independent Researcher +1
Doc-V*:Coarse-to-Fine Interactive Visual Reasoning for Multi-Page Document VQA
Apr 15, 2026Yuanlei Zheng, Pei Fu, Hang Li +9Document QA Long-Document VQA
School of Software Engineering, Huazhong University of Science and Technology · MiLM Plus, Xiaomi Inc. · School of Computer Science and Technology, Huazhong University of Science and Technology +1
MM-Doc-R1: Training Agents for Long Document Visual Question Answering through Multi-turn Reinforcement Learning
Apr 15, 2026Jiahang Lin, Kai Hu, Binghai Wang +12Long-Document VQA Multi-Turn RL
Fudan University · Shanghai Qiji Zhifeng Co., Ltd
DocSeeker: Structured Visual Reasoning with Evidence Grounding for Long Document Understanding
Apr 14, 2026Hao Yan, Yuliang Liu, Xingchen Liu +5Document Understanding Long-Document VQA
Huazhong University of Science and Technology · Huawei Inc.
Internalized Reasoning for Long-Context Visual Document Understanding
Mar 31, 2026Austin VeselkaMultimodal Understanding Document Image Understanding
LightOn
How to Train Your Long-Context Visual Document Model
Feb 16, 2026Austin VeselkaVisual Question Answering Vision-Language Models
LightOn

Oct 19, 2026J/K move · Enter open · S save

One Fact, Many Places: Redundant Evidence in Long Visual Documents Breaks Single-Gold Evaluation of Retrieval, Citation and Attribution

Xiaokang Yuan, Binhui Yao, Luwei Yang, Ruimin Chen+1

Zhejiang University, Hangzhou, China · Zhejiang Geely Holding Group Co., Ltd, Hangzhou, China

IR Evaluation Evidence Retrieval RAG Citation Faithfulness Long-Document VQA

Open paper AskPDF arXiv

Document understanding is increasingly judged on where an answer comes from, scored against annotated gold locations as if each fact lived in one place. In long visual documents, a fact often lives in several places: a chart value is restated in the text, a key figure reappears in the summary. We ask how often such copies occur in standard benchmarks and what they do to evaluation. We annotate 420 questions from MMLongBench-Doc and MMDocRAG with the locations that independently establish each required fact, checked by two independent reviewers. Copies are common and often cross-modal: 19.5% of MMLongBench-Doc test questions have a strict copy outside the gold, and in 28% of MMDocRAG questions a non-gold candidate alone supplies a required fact. Single-gold scoring then fails in three predictable ways. A retriever that finds a copy is scored as a miss: page recall@1 of text and visual retrievers is underestimated by 13-24 points on questions with a cross-page copy. A model that cites a copy is scored as citing wrongly: crediting equivalent evidence reverses 11% of pairwise orderings among 65 competitive MMDocRAG systems. Masking the gold region leaves the fact available elsewhere: with a copy in the input, 41-56% of correct answers across four models survive it yet fail once every annotated instance is masked. Set-level masking with automatically found copies closes 78% of the gap to masking every annotated instance at matched granularity (three models); an unverified key-string rule lowers survival at least as far but masks three times the area. We release the annotations and redundancy-aware metrics.