{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:27:13Z","timestamp":1783438033953,"version":"3.54.6"},"reference-count":51,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,15]],"date-time":"2023-12-15T00:00:00Z","timestamp":1702598400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,15]],"date-time":"2023-12-15T00:00:00Z","timestamp":1702598400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000185","name":"Defense Advanced Research Projects Agency","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,12,15]]},"DOI":"10.1109\/bigdata59044.2023.10386190","type":"proceedings-article","created":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T13:28:47Z","timestamp":1705930127000},"page":"875-884","source":"Crossref","is-referenced-by-count":4,"title":["Leveraging Large Language Models for Structure Learning in Prompted Weak Supervision"],"prefix":"10.1109","author":[{"given":"Jinyan","family":"Su","sequence":"first","affiliation":[{"name":"Cornell University,Ithaca,NY,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peilin","family":"Yu","sequence":"additional","affiliation":[{"name":"Brown University,Providence,RI,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jieyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Washington,Seattle,WA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stephen H.","family":"Bach","sequence":"additional","affiliation":[{"name":"Brown University,Providence,RI,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Data programming: Creating large training sets, quickly","volume":"29","author":"Ratner","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.14778\/3157794.3157797"},{"key":"ref3","article-title":"A survey on programmatic weak supervision","author":"Zhang","year":"2022","journal-title":"arXiv preprint arXiv:2202.05433"},{"key":"ref4","article-title":"Language models in the loop: Incorporating prompting into weak supervision","author":"Smith","year":"2022","journal-title":"arXiv preprint arXiv:2205.02318"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-demo.46"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3314036"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.14778\/3415478.3415559"},{"key":"ref8","article-title":"Overton: A data system for monitoring and improving machine-learned products","author":"R\u00e9","year":"2019","journal-title":"arXiv preprint arXiv:1909.05372"},{"key":"ref9","first-page":"8214","article-title":"Firebolt: Weak supervision under weaker assumptions","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Kuang"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6009"},{"key":"ref11","article-title":"Ask me anything: A simple strategy for prompting language models","author":"Arora","year":"2022","journal-title":"arXiv preprint arXiv:2210.02441"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.55"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1214\/009053606000000281"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/1835804.1835845"},{"key":"ref15","first-page":"273","article-title":"Learning the structure of generative models without labeled data","volume-title":"International Conference on Machine Learning","author":"Bach"},{"key":"ref16","article-title":"Inferring generative model structure with static analysis","volume":"30","author":"Varma","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref17","article-title":"Multitask prompted training enables zero-shot task generalization","author":"Sanh","year":"2021","journal-title":"arXiv preprint arXiv:2110.08207"},{"key":"ref18","first-page":"3280","article-title":"Fast and three-rious: Speeding up weak supervision with triplet methods","volume-title":"International Conference on Machine Learning","author":"Fu"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2488388.2488414"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2015.7113284"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/8291.001.0001"},{"key":"ref22","article-title":"Scalable semi-supervised aggregation of classifiers","volume":"28","author":"Balsubramani","year":"2015","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"1","key":"ref23","first-page":"3537","article-title":"Spectral methods meet em: A provably optimal algorithm for crowdsourcing","volume":"17","author":"Zhang","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/279943.279962"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3271737"},{"key":"ref26","article-title":"Learning from rules generalizing labeled exemplars","author":"Awasthi","year":"2020","journal-title":"arXiv preprint arXiv:2004.06025"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403149"},{"key":"ref28","first-page":"541","article-title":"Knowledge-based weak supervision for information extraction of overlapping relations","volume-title":"Proceedings of the 49th annual meeting of the association for computational linguistics: human language technologies","author":"Hoffmann"},{"key":"ref29","article-title":"Creating training sets via weak indirect supervision","author":"Zhang","year":"2021","journal-title":"arXiv preprint arXiv:2110.03484"},{"key":"ref30","article-title":"Learning from multiple noisy partial labelers","author":"Yu","year":"2022","journal-title":"Artificial Intelligence and Statistics (AISTATS)"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.139"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.555"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.801"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.5"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.190"},{"key":"ref37","article-title":"In-Pars: Data augmentation for information retrieval","author":"Bonifacio","year":"2022","journal-title":"arXiv preprint arXiv:2202.05144"},{"key":"ref38","article-title":"Co-training improves prompt-based learning for large language models","author":"Lang","year":"2022","journal-title":"arXiv preprint arXiv:2202.00828"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00410"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.55"},{"key":"ref41","article-title":"Dependency structure misspecification in multi-source weak supervision models","author":"Cachay","year":"2021","journal-title":"arXiv preprint arXiv:2106.10302"},{"key":"ref42","first-page":"6418","article-title":"Learning dependency structures for weak supervision models","volume-title":"International Conference on Machine Learning","author":"Varma"},{"key":"ref43","article-title":"Universalizing weak supervision","author":"Shin","year":"2021","journal-title":"arXiv preprint arXiv:2112.03865"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014763"},{"key":"ref45","article-title":"Multi-resolution weak supervision for sequential data","volume":"32","author":"Varma","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref46","article-title":"WRENCH: A comprehensive benchmark for weak supervision","volume-title":"Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track","author":"Zhang"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2015.37"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/1166160.1166191"},{"key":"ref49","first-page":"42","article-title":"What do a million news articles look like?","author":"Corney","year":"2016","journal-title":"NewsIR@ ECIR"},{"issue":"1","key":"ref50","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"The Journal of Machine Learning Research"},{"key":"ref51","article-title":"Roberta: A robustly optimized bert pretraining approach","author":"Liu","year":"2019","journal-title":"arXiv preprint arXiv:1907.11692"}],"event":{"name":"2023 IEEE International Conference on Big Data (BigData)","location":"Sorrento, Italy","start":{"date-parts":[[2023,12,15]]},"end":{"date-parts":[[2023,12,18]]}},"container-title":["2023 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10385234\/10386078\/10386190.pdf?arnumber=10386190","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T12:12:38Z","timestamp":1706011958000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10386190\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,15]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/bigdata59044.2023.10386190","relation":{},"subject":[],"published":{"date-parts":[[2023,12,15]]}}}