{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T15:47:29Z","timestamp":1774453649345,"version":"3.50.1"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,8,31]],"date-time":"2025-08-31T00:00:00Z","timestamp":1756598400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,31]],"date-time":"2025-08-31T00:00:00Z","timestamp":1756598400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,8,31]]},"DOI":"10.1109\/mlsp62443.2025.11204232","type":"proceedings-article","created":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T17:15:52Z","timestamp":1761326152000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["Multi-Agent Interactive Question Generation Framework for Long Document Understanding"],"prefix":"10.1109","author":[{"given":"Kesen","family":"Wang","sequence":"first","affiliation":[{"name":"Humain,Riyadh,KSA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daulet","family":"Toibazar","sequence":"additional","affiliation":[{"name":"Humain,Riyadh,KSA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abdulrahman","family":"Alfulayt","sequence":"additional","affiliation":[{"name":"Humain,Riyadh,KSA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abdulaziz S.","family":"Albadawi","sequence":"additional","affiliation":[{"name":"Humain,Riyadh,KSA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ranya A.","family":"Alkahtani","sequence":"additional","affiliation":[{"name":"Humain,Riyadh,KSA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Asma A.","family":"Ibrahim","sequence":"additional","affiliation":[{"name":"Humain,Riyadh,KSA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haneen A.","family":"Alhomoud","sequence":"additional","affiliation":[{"name":"Humain,Riyadh,KSA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sherif","family":"Mohamed","sequence":"additional","affiliation":[{"name":"Humain,Riyadh,KSA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pedro J.","family":"Moreno","sequence":"additional","affiliation":[{"name":"Humain,Riyadh,KSA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","author":"Team","year":"2024","journal-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context"},{"key":"ref3","year":"2024","journal-title":"Claude 3 haiku: Our fastest model yet"},{"key":"ref4","article-title":"Internlm-xcomposer-2\u20134khd: A pioneering large vision-language model handling resolutions from 336 pixels to 4 k hd","author":"Dong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref5","author":"Li","year":"2024","journal-title":"Llava-next: Stronger llms supercharge multimodal capabilities in the wild"},{"key":"ref6","article-title":"Cogvlm: Visual expert for pretrained language models","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00264"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548422"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01789"},{"key":"ref12","article-title":"Mmlongbench-doc: Benchmarking long-context document understanding with visualizations","author":"Ma","year":"2024","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.57"},{"key":"ref14","article-title":"M-longdoc: A benchmark for multimodal super-long document understanding and a retrieval-aware tuning framework","author":"Ken Chia","year":"2024","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"Camel-bench: A comprehensive arabic 1 mm benchmark","author":"Ghaboura","year":"2024","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539043"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.120"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-41679-8_9"},{"key":"ref19","article-title":"Document visual question answering challenge 2020","author":"Mathew","year":"2020","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680790"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2007.4376991"},{"key":"ref22","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"Blip-2: Bootstrapping language-image pretraining with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72640-8_7"},{"key":"ref25","article-title":"Automated annotation with generative ai requires validation","author":"Pangakis","year":"2023","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"Labelvizier: Error profiling and interactive data annotation for longdocument understanding","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.eacl-demo.18"},{"key":"ref28","article-title":"pdf2image: A python library to convert pdf pages to images using poppler","author":"Belval","year":"2018","journal-title":"GitHub repository"},{"key":"ref29","article-title":"Texthawk2: A large vision-language model excels in bilingual ocr and grounding with 16x fewer tokens","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref30","article-title":"Towards general ocr application via a vision-language model","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3390\/computers13120336"}],"event":{"name":"2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)","location":"Istanbul, Turkiye","start":{"date-parts":[[2025,8,31]]},"end":{"date-parts":[[2025,9,3]]}},"container-title":["2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11204201\/11204202\/11204232.pdf?arnumber=11204232","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T18:37:15Z","timestamp":1762367835000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11204232\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,31]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/mlsp62443.2025.11204232","relation":{},"subject":[],"published":{"date-parts":[[2025,8,31]]}}}