Elamur Research⌕
☰
home / papers / 2026 / WikiVideo: Article Generation from Multiple Videos

WikiVideo: Article Generation from Multiple Videos

Paper · 2026 · Alexander Martin, Reno Kriz, William Gantt Walden et al.

Summary

Video is a natural evidence source for retrieval-augmented generation, yet most article-generation work relies on text. Video summarization research mostly yields low-level scene descriptions rather than an account of the underlying event. The authors define a new task: writing a Wikipedia-lead-style article about a real-world event (disasters, elections, etc.) from several videos, with every claim traceable to visual, audio or OCR evidence. They release WikiVideo, built on MultiVENT 1.0/2.0 and linked Wikipedia leads from MegaWika2. To build it, they split each lead into atomic subclaims, had experts correct these and ground them in the videos, and then rewrote the lead so it keeps only supported content. They also propose Collaborative Article Generation (CAG). In CAG, a VideoLLM extracts details, an r1-style reasoning model filters them and asks for further extractions, and a text-only LLM merges the results into an article. CAG beats plain VideoLLMs with both oracle and retrieved videos. Results still drop sharply with real retrieval, and adding audio hurts. This leaves clear room for grounded multimodal writing tools, such as quick drafts of articles on unfolding events.

Key points

  • Dataset size: WikiVideo covers 57 events and 427 relevant videos, about 8 per event, drawn from a 109K-video corpus. The events span 2016–2025 and are split into WikiVideo-24 and WikiVideo-25 subsets to reduce parametric-memory effects.
  • Curation pipeline: the authors started from 63 events and 503 videos and removed six events whose grounded content was too thin. Subclaims were drafted with Qwen 2.5 32B and then corrected by experts.
  • Retrieval results: with the top-5 videos from Video-ColBERT or MMMORRF, CAG reaches R1 ≈ 24. With oracle videos it reaches R1 34.0 and BS 86.4.
  • Audio input: adding audio transcripts consistently lowered scores. It also shortened the generated articles (about 164 vs. 206 tokens).
  • Compute cost: the 72B CAG variant needs 8×80GB A100 GPUs even for single-video inference.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓Johns Hopkins UniversityBaltimore · United States240 works · 96,487 citations🎓University of Maryland, Baltimore CountyBaltimore · United States14 works · 915 citations

 Fields, topics and concepts

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksComputer Vision and Pattern Recognition · 2,869 works

Cite

Cite as Alexander Martin, Reno Kriz, William Gantt Walden, Kate Sanders, Hannah Recknor, Eugene Yang, Francis Ferraro and Benjamin Van Durme. 2026. WikiVideo: Article Generation from Multiple Videos. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.findings-acl.3

@inproceedings{martin2026wikivideo,
  title = {{WikiVideo: Article Generation from Multiple Videos}},
  author = {Alexander Martin, Reno Kriz, William Gantt Walden, Kate Sanders, Hannah Recknor, Eugene Yang, Francis Ferraro and Benjamin {Van Durme}},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.3},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.3}
}

References

53 references, 14 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. DeepSeek-AI, Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, Xiaokang Zhang, Xingkai Yu, Yu Wu, Z. F. Wu, Zhibin Gou, Zhihong Shao, Zhuoshu Li, Ziyi Gao, and 181 others. 2025. Deepseek-r1: Incentivizing reasoning capability in ll…
  2. Lisa Anne Hendricks, Oliver Wang, Eli Shechtman, Josef Sivic, Trevor Darrell, and Bryan Russell. 2017. Localizing moments in video with natural language. In Proceedings of the IEEE International Conference on Computer Vision (ICCV). find
  3. Shuai Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Sibo Song, Kai Dang, Peng Wang, Shijie Wang, Jun Tang, Humen Zhong, Yuanzhi Zhu, Mingkun Yang, Zhaohai Li, Jianqiang Wan, Pengfei Wang, Wei Ding, Zheren Fu, Yiheng Xu, and 8 others. 2025. Qwen2.5-vl technical report. Preprint, arXiv:2502.13…
  4. Xinya Du, Alexander Rush, and Claire Cardie. 2021. GRIT: Generative role-filler transformers for document-level event entity extraction. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 634–644, Online. Association for… find
  5. Samuel Barham, Chandler May, and Benjamin Van Durme. 2025. Megawika 2: A more comprehensive multilingual collection of articles and their sources. Preprint, arXiv:2508.03828. — [arXiv:2508.03828](https://arxiv.org/abs/2508.03828) find
  6. Alexander Fabbri, Irene Li, Tianwei She, Suyi Li, and Dragomir Radev. 2019. Multi-news: A large-scale multi-document summarization dataset and abstractive hierarchical model. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 1074–1084, Florence, Italy.…
  7. Samuel Barham, Orion Weller, Michelle Yuan, Kenton Murray, Mahsa Yarmohammadi, Zhengping Jiang, Siddharth Vashishtha, Alexander Martin, Anqi Liu, Aaron Steven White, Jordan Boyd-Graber, and Benjamin Van Durme. 2023. Megawika: Millions of 53 9 find
  8. William Gantt, Alexander Martin, Pavlo Kuchmiichuk, and Aaron Steven White. 2024. Event-keyed summarization. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 7333–7345, Miami, Florida, USA. Association for Computational Linguistics. find
  9. William Jurayj, Jeffrey Cheng, and Benjamin Van Durme. 2025. Is that your final answer? test-time scaling improves selective question answering. Preprint, arXiv:2502.13962.
  10. Ranjay Krishna, Kenji Hata, Frederic Ren, Li Fei-Fei, and Juan Carlos Niebles. 2017. Dense-captioning events in videos. In Proceedings of the IEEE International Conference on Computer Vision (ICCV). find
  11. Anisha Gunjal and Greg Durrett. 2024. Molecular facts: Desiderata for decontextualization in LLM fact verification. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 3751–3768, Miami, Florida, USA. Association for Computational Linguistics. find
  12. Reno Kriz, Kate Sanders, David Etter, Kenton Murray, Cameron Carpenter, Kelly Van Ochten, Hannah Recknor, Jimena Guallar-Blasco, Alexander Martin, Ronald Colaianni, Nolan King, Eugene Yang, and Benjamin Van Durme. 2024. Multivent 2.0: A massive multilingual benchmark for event-centric video retrieva… — [arXiv:2410.11619](https://arxiv.org/abs/2410.11619) find
  13. Michael Gygli, Helmut Grabner, Hayko Riemenschneider, and Luc Van Gool. 2014. Creating summaries from user videos. In Computer Vision – ECCV 2014, pages 505–520, Cham. Springer International Publishing. find
  14. Dawn Lawrie, Sean MacAvaney, James Mayfield, Paul McNamee, Douglas W. Oard, and Luca Soldaini åand Eugene Yang. 2024. Overview of the trec 2023 neuclir track. Preprint, arXiv:2404.08071. — [arXiv:2404.08071](https://arxiv.org/abs/2404.08071) find
  15. Bo He, Jun Wang, Jielin Qiu, Trung Bui, Abhinav Shrivastava, and Zhaowen Wang. 2023. Align and Attend: Multimodal Summarization with Dual Contrastive Losses . In 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 14867–14878, Los Alamitos, CA, USA. IEEE Computer Societ… find
  16. Jie Lei, Licheng Yu, Mohit Bansal, and Tamara Berg. 2018. TVQA: Localized, compositional video question answering. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 1369–1379, Brussels, Belgium. Association for Computational Linguistics.
  17. Karl Moritz Hermann, Tomas Kocisky, Edward Grefenstette, Lasse Espeholt, Will Kay, Mustafa Suleyman, and Phil Blunsom. 2015. Teaching machines to read and comprehend. Advances in neural information processing systems, 28.
  18. Guangyao Li, Yake Wei, Yapeng Tian, Chenliang Xu, Ji-Rong Wen, and Di Hu. 2022. Learning to answer questions in dynamic audio-visual scenarios. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 19108–19118. find
  19. Qisheng Hu, Quanyu Long, and Wenya Wang. 2025. Decomposition dilemmas: Does claim decomposition boost or burden fact-checking performance? Preprint, arXiv:2411.02400. find
  20. Xinhao Li, Yi Wang, Jiashuo Yu, Xiangyu Zeng, Yuhan Zhu, Haian Huang, Jianfei Gao, Kunchang Li, Yinan He, Chenting Wang, Yu Qiao, Yali Wang, and Limin Wang. 2025. Videochat-flash: Hierarchical compression for long-context video modeling. Preprint, arXiv:2501.00574. — [arXiv:2501.00574](https://arxiv.org/abs/2501.00574) find
  21. Hang Hua, Yunlong Tang, Chenliang Xu, and Jiebo Luo. 2024. V2xum-llm: Cross-modal video summarization with temporal prompt instruction tuning. Preprint, arXiv:2404.12353. — [arXiv:2404.12353](https://arxiv.org/abs/2404.12353) find
  22. Kung-Hsiang Huang, Philippe Laban, Alexander Fabbri, Prafulla Kumar Choubey, Shafiq Joty, Caiming Xiong, and Chien-Sheng Wu. 2024. Embrace divergence for richer insights: A multi-document summarization benchmark and a case study on summarizing diverse information from news articles. In Proceedings o… find
  23. Chin-Yew Lin. 2004. ROUGE: A package for automatic evaluation of summaries. In Text Summarization Branches Out, pages 74–81, Barcelona, Spain. Association for Computational Linguistics.
  24. Jingyang Lin, Hang Hua, Ming Chen, Yikang Li, Jenhao Hsiao, Chiuman Ho, and Jiebo Luo. 2024. Videoxum: Cross-modal visual and textural summarization of videos. IEEE Transactions on Multimedia, 26:5548–5560. find
  25. Peter J. Liu, Mohammad Saleh, Etienne Pot, Ben Goodrich, Ryan Sepassi, Lukasz Kaiser, and Noam Shazeer. 2018a. Generating wikipedia by summarizing long sequences. In International Conference on Learning Representations.
  26. Wenxuan Huang, Bohan Jia, Zijie Zhai, Shaosheng Cao, Zheyu Ye, Fei Zhao, Zhe Xu, Yao Hu, and Shaohui Lin. 2025. Vision-r1: Incentivizing reasoning capability in multimodal large language models. Preprint, arXiv:2503.06749. find
  27. Peter J. Liu, Mohammad Saleh, Etienne Pot, Ben Goodrich, Ryan Sepassi, Lukasz Kaiser, and Noam M. Shazeer. 2018b. Generating wikipedia by summarizing long sequences. ArXiv, abs/1801.10198.
  28. Yunseok Jang, Yale Song, Youngjae Yu, Youngjin Kim, and Gunhee Kim. 2017. Tgif-qa: Toward spatiotemporal reasoning in visual question answering. Preprint, arXiv:1704.04497. 54 10 find
  29. Sewon Min, Kalpesh Krishna, Xinxi Lyu, Mike Lewis, Wen-tau Yih, Pang Koh, Mohit Iyyer, Luke Zettlemoyer, and Hannaneh Hajishirzi. 2023. FActScore: Fine-grained atomic evaluation of factual precision in long form text generation. In Proceedings of the 2023 Conference on Empirical Methods in Natural L…
  30. Christina Sauper and Regina Barzilay. 2009. Automatically generating Wikipedia articles: A structure-aware approach. In Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP, pages 208–216, Sun… find
  31. Ramesh Nallapati, Bowen Zhou, Cicero dos Santos, Çağlar Gu˙lçehre, and Bing Xiang. 2016. Abstractive text summarization using sequence-to-sequence RNNs and beyond. In Proceedings of the 20th SIGNLL Conference on Computational Natural Language Learning, pages 280–290, Berlin, Germany. Association fo…
  32. Yijia Shao, Yucheng Jiang, Theodore A. Kanell, Peter Xu, Omar Khattab, and Monica S. Lam. 2024. Assisting in writing wikipedia-like articles from scratch with large language models. Preprint, arXiv:2402.14207.
  33. Luca Soldaini, Rodney Kinney, Akshita Bhagia, Dustin Schwenk, David Atkinson, Russell Authur, Ben Bogin, Khyathi Chandu, Jennifer Dumas, Yanai Elazar, Valentin Hofmann, Ananya Jha, Sachin Kumar, Li Lucy, Xinxi Lyu, Nathan Lambert, Ian Magnusson, Jacob Morrison, Niklas Muennighoff, and 17 others. 202… find
  34. Qwen, :, An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, Huan Lin, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Yang, Jiaxi Yang, Jingren Zhou, and 25 others. 2025. Qwen2.5 technical report. Preprint, arXiv:2412.15115. find
  35. Alec Radford, Jong Wook Kim, Tao Xu, Greg Brockman, Christine McLeavey, and Ilya Sutskever. 2022. Robust speech recognition via large-scale weak supervision. arXiv preprint.
  36. Yale Song, Jordi Vallmitjana, Amanda Stent, and Alejandro Jaimes. 2015. Tvsum: Summarizing web videos using titles. In 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 5179–5187. find
  37. Arun Reddy, Alexander Martin, Eugene Yang, Andrew Yates, Kate Sanders, Kenton Murray, Reno Kriz, Celso M. de Melo, Benjamin Van Durme, and Rama Chellappa. 2025. Video-colbert: Contextualized late interaction for text-to-video retrieval. Preprint, arXiv:2503.19009. — [arXiv:2503.19009](https://arxiv.org/abs/2503.19009) find
  38. Neha Srikanth and Rachel Rudinger. 2025. Nli under the microscope: What atomic hypothesis decomposition reveals. Preprint, arXiv:2502.08080.
  39. Xubin Ren, Lingrui Xu, Long Xia, Shuaiqiang Wang, Dawei Yin, and Chao Huang. 2025. Videorag: Retrieval-augmented generation with extreme long-context videos. Preprint, arXiv:2502.01549. — [arXiv:2502.01549](https://arxiv.org/abs/2502.01549) find
  40. Sai Vallurupalli, Sayontan Ghosh, Katrin Erk, Niranjan Balasubramanian, and Francis Ferraro. 2022. POQue: Asking participant-specific outcome questions for a deeper understanding of complex events. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 8674–… find
  41. J. J. Rocchio. 1971. Relevance feedback in information retrieval. find
  42. Saron Samuel, Dan DeGenaro, Jimena Guallar-Blasco, Kate Sanders, Oluwaseun Eisape, Arun Reddy, Alexander Martin, Andrew Yates, Eugene Yang, Cameron Carpenter, David Etter, Efsun Kayi, Matthew Wiesner, Kenton Murray, and Reno Kriz. 2025. Mmmorrf: Multimodal multilingual modularized reciprocal rank fu… — [arXiv:2503.20698](https://arxiv.org/abs/2503.20698) find
  43. Siddharth Vashishtha, Alexander Martin, William Gantt, Benjamin Van Durme, and Aaron White. 2024. FA-MuS: Frames across multiple sources. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long… find
  44. Kate Sanders, David Etter, Reno Kriz, and Benjamin Van Durme. 2023. MultiVENT: Multilingual videos of events and aligned natural text. In Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track. find
  45. William Walden, Pavlo Kuchmiichuk, Alexander Martin, Chihsheng Jin, Angela Cao, Claire Sun, Curisia Allen, and Aaron Steven White. 2024. Cross-document event-keyed summarization. Preprint, arXiv:2410.14795. find
  46. Kate Sanders, Reno Kriz, David Etter, Hannah Recknor, Alexander Martin, Cameron Carpenter, Jingyang Lin, and Benjamin Van Durme. 2024. Grounding partially-defined events in multimodal data. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 15905–15927, Miami, Florida, U… find
  47. Xin Wang, Jiawei Wu, Junkun Chen, Lei Li, Yuan-Fang Wang, and William Yang Wang. 2020. Vatex: A large-scale, high-quality multilingual 55 11 dataset for video-and-language research. Preprint, arXiv:1904.03493. instruction tuning with synthetic data. arXiv:2410.02713. find
  48. Preprint, Yuanhan Zhang, Jinming Wu, Wei Li, Bo Li, Zejun MA, Ziwei Liu, and Chunyuan Li. 2024b. Video instruction tuning with synthetic data. find
  49. Yi Wang, Xinhao Li, Ziang Yan, Yinan He, Jiashuo Yu, Xiangyu Zeng, Chenting Wang, Changlian Ma, Haian Huang, Jianfei Gao, Min Dou, Kai Chen, Wenhai Wang, Yu Qiao, Yali Wang, and Limin Wang. 2025. Internvideo2.5: Empowering video mllms with long and rich context modeling. Preprint, arXiv:2501.12386. — [arXiv:2501.12386](https://arxiv.org/abs/2501.12386) find
  50. Luowei Zhou, Yannis Kalantidis, Xinlei Chen, Jason J. Corso, and Marcus Rohrbach. 2019. Grounded video description. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). find
  51. Miriam Wanner, Benjamin Van Durme, and Mark Dredze. 2024a. Dndscore: Decontextualization and decomposition for factuality verification in long-form text generation. Preprint, arXiv:2412.13175. find
  52. Fangwei Zhu, Shangqing Tu, Jiaxin Shi, Juanzi Li, Lei Hou, and Tong Cui. 2021. TWAG: A topic-guided Wikipedia abstract generator. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Vol… find
  53. Miriam Wanner, Seth Ebner, Zhengping Jiang, Mark Dredze, and Benjamin Van Durme. 2024b. A closer look at claim decomposition. In Proceedings of the 13th Joint Conference on Lexical and Computational Semantics (*SEM 2024), pages 153–175, Mexico City, Mexico. Association for Computational Linguistics. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/martin-2026-wikivideo-article-generation-multiple-videos/