{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T22:33:08Z","timestamp":1777415588890,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":11,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,5,8]],"date-time":"2025-05-08T00:00:00Z","timestamp":1746662400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100006374","name":"Australian Research Council","doi-asserted-by":"publisher","award":["IC200100022"],"award-info":[{"award-number":["IC200100022"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,5,8]]},"DOI":"10.1145\/3701716.3717568","type":"proceedings-article","created":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T16:12:56Z","timestamp":1748016776000},"page":"2129-2132","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Are Large Language Models Good Data Preprocessors?"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1978-686X","authenticated-orcid":false,"given":"Elyas","family":"Meguellati","sequence":"first","affiliation":[{"name":"The University of Queensland, Brisbane, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8710-4653","authenticated-orcid":false,"given":"Nardiena","family":"Pratama","sequence":"additional","affiliation":[{"name":"The University of Queensland, Brisbane, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6739-4145","authenticated-orcid":false,"given":"Shazia","family":"Sadiq","sequence":"additional","affiliation":[{"name":"The University of Queensland, Brisbane, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7311-3693","authenticated-orcid":false,"given":"Gianluca","family":"Demartini","sequence":"additional","affiliation":[{"name":"The University of Queensland, Brisbane, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,5,23]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Multi-Sentence Documents. arXiv preprint arXiv:1904.07826","author":"Hessel Jack","year":"2019","unstructured":"Jack Hessel, David Mimno, and Lillian Lee. 2019. Unsupervised Discovery of Multimodal Links in Multi-Image, Multi-Sentence Documents. arXiv preprint arXiv:1904.07826 (2019)."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00788--1"},{"key":"e_1_3_2_2_3_1","volume-title":"Li","author":"Junnan","year":"2022","unstructured":"Junnan et al. Li. 2022. BLIP: Bootstrapped Learning from Image-Text Pairs. arXiv preprint arXiv:2201.12086 (2022)."},{"key":"e_1_3_2_2_4_1","volume-title":"Liang","author":"Jiayi","year":"2023","unstructured":"Jiayi et al. Liang. 2023. LLMs as Data Analysts: A Review of Analytical Capabilities. NVIDIA Developer Blog (2023). Available at: https:\/\/developer.nvidia.com\/blog\/build-an-llm-powered-data-agent-for-data-analysis\/."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-023-00952-2"},{"key":"e_1_3_2_2_6_1","volume-title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks. arXiv preprint arXiv:1908.02265","author":"Lu Jiasen","year":"2019","unstructured":"Jiasen Lu, Dhruv Batra, Devi Parikh, and Stefan Lee. 2019. ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks. arXiv preprint arXiv:1908.02265 (2019)."},{"key":"e_1_3_2_2_7_1","volume-title":"Rahman","author":"Anik","year":"2023","unstructured":"Anik et al. Rahman. 2023. Data Wrangling with LLMs: An Evaluation of Capabilities. arXiv preprint arXiv:2308.16361 (2023)."},{"key":"e_1_3_2_2_8_1","volume-title":"Wang","author":"Xinlei","year":"2022","unstructured":"Xinlei et al. Wang. 2022. GIT: A Generative Image Transformer for Multimodal Learning. arXiv preprint arXiv:2203.02053 (2022)."},{"key":"e_1_3_2_2_9_1","volume-title":"Jellyfish: A Large Language Model for Data Preprocessing. arXiv:2312.01678 [cs.AI] https:\/\/arxiv.org\/abs\/2312.01678","author":"Zhang Haochen","year":"2024","unstructured":"Haochen Zhang, Yuyang Dong, Chuan Xiao, and Masafumi Oyamada. 2024. Jellyfish: A Large Language Model for Data Preprocessing. arXiv:2312.01678 [cs.AI] https:\/\/arxiv.org\/abs\/2312.01678"},{"key":"e_1_3_2_2_10_1","unstructured":"Haochen Zhang Yuyang Dong Chuan Xiao and Masafumi Oyamada. 2024. Large Language Models as Data Preprocessors. arXiv:2308.16361 [cs.AI] https:\/\/arxiv.org\/abs\/2308.16361"},{"key":"e_1_3_2_2_11_1","volume-title":"Zhong","author":"Victor","year":"2023","unstructured":"Victor et al. Zhong. 2023. A Comprehensive Study of LLMs for SQL Query Generation. arXiv preprint arXiv:2406.08426 (2023)."}],"event":{"name":"WWW '25: The ACM Web Conference 2025","location":"Sydney NSW Australia","acronym":"WWW '25","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Companion Proceedings of the ACM on Web Conference 2025"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3701716.3717568","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3701716.3717568","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T03:05:24Z","timestamp":1759892724000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3701716.3717568"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,8]]},"references-count":11,"alternative-id":["10.1145\/3701716.3717568","10.1145\/3701716"],"URL":"https:\/\/doi.org\/10.1145\/3701716.3717568","relation":{},"subject":[],"published":{"date-parts":[[2025,5,8]]},"assertion":[{"value":"2025-05-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}