{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T23:18:30Z","timestamp":1787872710574,"version":"build-2784847793"},"reference-count":30,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,21]]},"DOI":"10.1109\/vis54172.2023.00056","type":"proceedings-article","created":{"date-parts":[[2023,12,20]],"date-time":"2023-12-20T14:20:07Z","timestamp":1703082007000},"page":"236-240","source":"Crossref","is-referenced-by-count":12,"title":["Visualizing Linguistic Diversity of Text Datasets Synthesized by Large Language Models"],"prefix":"10.1109","author":[{"given":"Emily","family":"Reif","sequence":"first","affiliation":[{"name":"Google Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minsuk","family":"Kahng","sequence":"additional","affiliation":[{"name":"Google Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Savvas","family":"Petridis","sequence":"additional","affiliation":[{"name":"Google Research"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"PaLM 2 technical report","volume-title":"arXiv preprint arXiv:2305.10403","author":"Anil","year":"2023"},{"key":"ref2","article-title":"Large scale qualitative evaluation of generative image model outputs","author":"Assogba","year":"2023","journal-title":"arXiv preprint arXiv:2301.04518"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2022.3209425"},{"key":"ref4","article-title":"Language models are realistic tabular data generators","author":"Borisov","year":"2022","journal-title":"arXiv preprint arXiv:2210.06280"},{"key":"ref5","article-title":"The role of interactive visualization in explaining (large) NLP models: from data to inference","author":"Brath","year":"2023","journal-title":"arXiv preprint arXiv:2301.04528"},{"key":"ref6","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2010.154"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1177\/1473871620904671"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2013.212"},{"key":"ref10","volume-title":"Visual text analytics: Report from dagstuhl seminar 22191","author":"Collins","year":"2022"},{"key":"ref11","first-page":"497","article-title":"Visualization of text document corpus","volume":"29","author":"Fortuna","year":"2005","journal-title":"Informatica (Slovenia)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.woah-1.20"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-020-00977-1"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/icde.2001.914830"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.512"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2018.2843369"},{"key":"ref17","volume-title":"spaCy 2: Natural language understanding with Bloom embeddings, convolutional neural networks and incremental parsing","author":"Honnibal","year":"2017"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/PACIFICVIS.2015.7156366"},{"key":"ref19","article-title":"Evaluation of synthetic datasets for conversational recommender systems","author":"Lara","year":"2022","journal-title":"arXiv preprint arXiv:2212.08167"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/191666.191776"},{"key":"ref21","article-title":"Visualizing and measuring the geometry of BERT","volume":"32","author":"Reif","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","article-title":"Bloom: A 176bparameter open-access multilingual language model","author":"Scao","year":"2023","journal-title":"arXiv preprint arXiv:2211.05100"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1057\/palgrave.ivs.9500180"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2017.2744158"},{"key":"ref25","article-title":"Does synthetic data generation of llms help clinical text mining?","author":"Tang","year":"2023","journal-title":"arXiv preprint arXiv:2303.04360"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.15"},{"key":"ref27","volume-title":"Evaluating synthetic code-switched data","author":"Vijayakumar","year":"2022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2008.172"},{"key":"ref29","article-title":"Synthbio: A case study in human-ai collaborative curation of text datasets","author":"Yuan","year":"2021","journal-title":"arXiv preprint arXiv:2111.06467"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-020-0191-7"}],"event":{"name":"2023 IEEE Visualization and Visual Analytics (VIS)","location":"Melbourne, Australia","start":{"date-parts":[[2023,10,21]]},"end":{"date-parts":[[2023,10,27]]}},"container-title":["2023 IEEE Visualization and Visual Analytics (VIS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10360877\/10360490\/10360888.pdf?arnumber=10360888","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T15:23:51Z","timestamp":1705073031000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10360888\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,21]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/vis54172.2023.00056","relation":{},"subject":[],"published":{"date-parts":[[2023,10,21]]}}}