{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T01:39:05Z","timestamp":1772933945533,"version":"3.50.1"},"reference-count":71,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"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":[[2025,12,8]]},"DOI":"10.1109\/bigdata66926.2025.11402173","type":"proceedings-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T20:57:57Z","timestamp":1772830677000},"page":"7370-7379","source":"Crossref","is-referenced-by-count":0,"title":["Survey of Generative Artificial Intelligence Powered Human-Data Interfaces in Big Data Systems"],"prefix":"10.1109","author":[{"given":"Yuzhuo","family":"Gao","sequence":"first","affiliation":[{"name":"Sserly Software"}]},{"given":"Abinas","family":"Roy","sequence":"additional","affiliation":[{"name":"Unaffiliated"}]},{"given":"Vishal","family":"Chodnekar","sequence":"additional","affiliation":[{"name":"Sserly Software"}]},{"given":"Chetan","family":"Solur","sequence":"additional","affiliation":[{"name":"Unaffiliated"}]},{"given":"Guanzhong","family":"Pan","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.2307\/41703503"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.1819486"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CESYS.2016.7889917"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1080\/2573234X.2018.1507605"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1080\/24751448.2018.1497381"},{"key":"ref6","volume-title":"Jupyter","year":"2019"},{"key":"ref7","volume-title":"Zeppelin","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/d41586-018-07196-1"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MSR.2019.00077"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3299887.3299897"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-33702-5_1"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2839509.2844560"},{"key":"ref13","article-title":"Matplotagent: Method and evaluation for 11 m -based agentic scientific data visualization","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3654992"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3329071"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1201\/9781003559139-3"},{"key":"ref17","volume-title":"Langchain: A framework for llm application development"},{"key":"ref18","volume-title":"Llamaindex: Llm-centric data indexing and retrieval framework"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1425"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/MCG.2024.3362168"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.visinf.2024.04.003"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3368621"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.71465\/fbf262"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.32996\/jcsts.2024.6.1.26"},{"issue":"1","key":"ref25","first-page":"122","article-title":"Harnessing generative ai for automated data analytics in business intelligence and decision-making","volume":"4","author":"Ravichandran","year":"2024","journal-title":"Hong Kong Journal of AI and Medicine"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4603227"},{"key":"ref27","author":"Luqman","year":"2025","journal-title":"Agentic ai in finance: A comprehensive overview"},{"key":"ref28","volume-title":"Pandas AI","year":"2025"},{"key":"ref29","volume-title":"Julius AI","year":"2025"},{"key":"ref30","article-title":"Datagpt-sql-7b: An opensource language model for text-to-sql","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s00607-015-0480-7"},{"key":"ref32","volume-title":"A detailed view inside snowflake. Technical report, Snowflake","year":"2017"},{"key":"ref33","volume-title":"Snowflake cortex","year":"2025"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3552039"},{"key":"ref35","first-page":"17","article-title":"Apache lucene 4","volume-title":"SIGIR 2012 workshop on open source information retrieval","author":"Bia\u0142ecki","year":"2012"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/MS.2023.3339408"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CAIN66642.2025.00034"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-90341-0_3"},{"key":"ref39","volume-title":"Cursor - The AI Code Editor","year":"2025"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3545945.3569830"},{"key":"ref41","author":"Brown","year":"2020","journal-title":"Language models are few-shot learners"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9891914"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00704"},{"key":"ref44","article-title":"Improving language understanding by generative pre-training","volume-title":"Technical report, OpenAI","author":"Radford","year":"2018"},{"key":"ref45","article-title":"Assessment of capex and opex for media services in cloud-enabled 5g networks","volume-title":"Journal \/ Conference Unknown, 2019. Discusses continual operational expenditure (OpEx) in cloud-enabled 5G networks"},{"key":"ref46","article-title":"The pii problem: Privacy and a new concept of personally identifiable information","author":"Solove","journal-title":"University law review \/ legal journal, 2011. Discusses issues with defining PII and proposes"},{"key":"ref47","author":"Carlini","year":"2021","journal-title":"Extracting training data from large language models"},{"key":"ref48","volume-title":"What is a virtual private cloud (vpc)","year":"2025"},{"key":"ref49","author":"Lewis","year":"2021","journal-title":"Retrievalaugmented generation for knowledge-intensive nlp tasks"},{"key":"ref50","author":"Sanh","year":"2020","journal-title":"Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter"},{"key":"ref51","author":"Xiao","year":"2024","journal-title":"Efficient streaming language models with attention sinks"},{"key":"ref52","article-title":"In-depth analysis of 11 m -based schema linking","volume-title":"Proceedings of the International Conference on Extending Database Technology (EDBT)","author":"Katsogiannis-Meimarakis","year":"2026"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3725337"},{"key":"ref54","article-title":"The impact of ai on developer productivity: Evidence from github copilot","author":"Peng","year":"2023","journal-title":"arXiv preprint"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s42486-023-00144-7"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2025.3567131"},{"key":"ref57","article-title":"A comprehensive survey on vector database: Storage and retrieval technique","author":"Ma","year":"2025","journal-title":"challenge"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s13222-023-00445-2"},{"key":"ref59","author":"Han","year":"2024","journal-title":"Parameter-efficient fine-tuning for large models: A comprehensive survey"},{"key":"ref60","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations (ICLR)","author":"Hu","year":"2022"},{"key":"ref61","first-page":"1","article-title":"Agentai: A comprehensive survey on autonomous agents","volume":"35","author":"Piccialli","year":"2025","journal-title":"Journal of Artificial Intelligence Research"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.comcom.2024.07.015"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2025.3609486"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3514221.3526045"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.14778\/3415478.3415568"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.1622"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/mcse.2007.55"},{"key":"ref68","article-title":"Creating plots with python and plotly","volume-title":"Wired","year":"2013"},{"key":"ref69","author":"Pan","year":"2025","journal-title":"A cost-benefit analysis of on-premise large language model deployment: Breaking even with commercial llm services"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.420"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/jiot.2024.3524255"}],"event":{"name":"2025 IEEE International Conference on Big Data (BigData)","location":"Macau, China","start":{"date-parts":[[2025,12,8]]},"end":{"date-parts":[[2025,12,11]]}},"container-title":["2025 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11400704\/11400712\/11402173.pdf?arnumber=11402173","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T06:55:55Z","timestamp":1772866555000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11402173\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,8]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/bigdata66926.2025.11402173","relation":{},"subject":[],"published":{"date-parts":[[2025,12,8]]}}}