{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T05:47:22Z","timestamp":1777873642625,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100006374","name":"Israel Science Foundation","doi-asserted-by":"publisher","award":["1702\/24"],"award-info":[{"award-number":["1702\/24"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Scharf-Ullman Endowment"},{"name":"Alon Scholarship"},{"DOI":"10.13039\/501100006374","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","award":["RGPIN-2025-04724,DGECR-2025-00373"],"award-info":[{"award-number":["RGPIN-2025-04724,DGECR-2025-00373"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006374","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["IIS-2420691,IIS-2420577,IIS-2147061"],"award-info":[{"award-number":["IIS-2420691,IIS-2420577,IIS-2147061"]}],"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":[[2025,8,3]]},"DOI":"10.1145\/3711896.3737102","type":"proceedings-article","created":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T13:30:13Z","timestamp":1754055013000},"page":"1318-1329","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Refining Labeling Functions with Limited Labeled Data"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-6849-3146","authenticated-orcid":false,"given":"Chenjie","family":"Li","sequence":"first","affiliation":[{"name":"University of Illinois Chicago, Chicago, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3764-1958","authenticated-orcid":false,"given":"Amir","family":"Gilad","sequence":"additional","affiliation":[{"name":"Hebrew University, Jerusalem, Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2887-2452","authenticated-orcid":false,"given":"Boris","family":"Glavic","sequence":"additional","affiliation":[{"name":"University of Illinois Chicago, Chicago, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2371-1186","authenticated-orcid":false,"given":"Zhengjie","family":"Miao","sequence":"additional","affiliation":[{"name":"Simon Fraser University, Burnaby, BC, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8300-7891","authenticated-orcid":false,"given":"Sudeepa","family":"Roy","sequence":"additional","affiliation":[{"name":"Duke University, Durham, NC, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,8,3]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1002\/spy2.9"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/2034691.2034742"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.14778\/3626292.3626294"},{"key":"e_1_3_2_2_4_1","volume-title":"Interactive Weak Supervision: Learning Useful Heuristics for Data Labeling. In International Conference on Learning Representations.","author":"Boecking Benedikt","year":"2021","unstructured":"Benedikt Boecking, Willie Neiswanger, Eric Xing, and Artur Dubrawski. 2021. Interactive Weak Supervision: Learning Useful Heuristics for Data Labeling. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_5_1","unstructured":"Bradley Butcher Miri Zilka Darren Cook Jiri Hron and Adrian Weller. 2023. Optimising Human-Machine Collaboration for Efficient High-Precision Information Extraction from Text Documents. arXiv preprint arXiv:2302.09324(2023)."},{"key":"e_1_3_2_2_6_1","volume-title":"Krishnaram Kenthapadi, and Adam Tauman Kalai.","author":"De-Arteaga Maria","year":"2019","unstructured":"Maria De-Arteaga, Alexey Romanov, Hanna M. Wallach, Jennifer T. Chayes, Christian Borgs, Alexandra Chouldechova, Sahin Cem Geyik, Krishnaram Kenthapadi, and Adam Tauman Kalai. 2019. Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting. In FAT, danah boyd and Jamie H. Morgenstern(Eds.). 120-128."},{"key":"e_1_3_2_2_7_1","first-page":"2334","article-title":"Witan","volume":"15","author":"Denham Benjamin","year":"2022","unstructured":"Benjamin Denham, Edmund M.-K. Lai, Roopak Sinha, and M. Asif Naeem. 2022. Witan: Unsupervised Labelling Function Generation for Assisted Data Programming. PVLDB, Vol. 15, 11 (2022), 2334-2347.","journal-title":"Unsupervised Labelling Function Generation for Assisted Data Programming. PVLDB"},{"key":"e_1_3_2_2_8_1","volume-title":"International conference on machine learning. PMLR, 3280-3291","author":"Fu Daniel","year":"2020","unstructured":"Daniel Fu, Mayee Chen, Frederic Sala, Sarah Hooper, Kayvon Fatahalian, and Christopher R\u00e9. 2020. Fast and three-rious: Speeding up weak supervision with triplet methods. In International conference on machine learning. PMLR, 3280-3291."},{"key":"e_1_3_2_2_9_1","first-page":"2217","article-title":"Adaptive Rule Discovery for Labeling Text Data","author":"Galhotra Sainyam","year":"2021","unstructured":"Sainyam Galhotra, Behzad Golshan, and Wang-Chiew Tan. 2021. Adaptive Rule Discovery for Labeling Text Data. In SIGMOD. 2217-2225.","journal-title":"SIGMOD."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898717730"},{"key":"e_1_3_2_2_11_1","first-page":"226","volume-title":"Proceedings 28th International Conference on Extending Database Technology, EDBT 2025","author":"Guan Naiqing","year":"2025","unstructured":"Naiqing Guan, Kaiwen Chen, and Nick Koudas. 2025. DataSculpt: Cost-Efficient Label Function Design via Prompting Large Language Models. In Proceedings 28th International Conference on Extending Database Technology, EDBT 2025, Barcelona, Spain, March 25-28, 2025. OpenProceedings.org, 226-232."},{"key":"e_1_3_2_2_12_1","volume-title":"Weshap: Weak Supervision Source Evaluation With Shapley Values. CoRR","author":"Guan Naiqing","year":"2024","unstructured":"Naiqing Guan and Nick Koudas. 2024. Weshap: Weak Supervision Source Evaluation With Shapley Values. CoRR, Vol. abs\/2406.11010 (2024). arXiv:2406.11010"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1175"},{"key":"e_1_3_2_2_14_1","volume-title":"McAuley","author":"He Ruining","year":"2016","unstructured":"Ruining He and Julian J. McAuley. 2016. Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering. In WWW, Jacqueline Bourdeau, Jim Hendler, Roger Nkambou, Ian Horrocks, and Ben Y. Zhao(Eds.). 507-517."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.14778\/3565838.3565859"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-011-9272-4"},{"key":"e_1_3_2_2_17_1","first-page":"141","volume-title":"Proceedings of the sixth BioCreative challenge evaluation workshop","volume":"1","author":"Krallinger Martin","year":"2017","unstructured":"Martin Krallinger, Obdulia Rabal, Saber A Akhondi, Martin P\u00e9rez P\u00e9rez, Jes\u00fas Santamar\u00eda, Gael P\u00e9rez Rodr\u00edguez, Georgios Tsatsaronis, Ander Intxaurrondo, Jos\u00e9 Antonio L\u00f3pez, Umesh Nandal, et al., 2017. Overview of the BioCreative VI chemical-protein interaction Track. In Proceedings of the sixth BioCreative challenge evaluation workshop, Vol. 1. 141-146."},{"key":"e_1_3_2_2_18_1","unstructured":"Chenjie Li Amir Gilad Boris Glavic Zhengjie Miao and Sudeepa Roy. 2025. Refining Labeling Functions with Limited Labeled Data. arxiv:2505.23470 [cs.LG] https:\/\/arxiv.org\/abs\/2505.23470"},{"key":"e_1_3_2_2_19_1","volume-title":"Proceedings of Workshops at the 50th International Conference on Very Large Data Bases, VLDB 2024","author":"Li Chenjie","year":"2024","unstructured":"Chenjie Li, Dan Zhang, and Jin Wang. 2024. LLM-assisted Labeling Function Generation for Semantic Type Detection. In Proceedings of Workshops at the 50th International Conference on Very Large Data Bases, VLDB 2024, Guangzhou, China, August 26-30, 2024."},{"key":"e_1_3_2_2_20_1","volume-title":"Automatic Rule Refinement for Information Extraction. PVLDB","volume":"3","author":"Liu B.","year":"2010","unstructured":"B. Liu, L. Chiticariu, V. Chu, HV Jagadish, and F.R. Reiss. 2010. Automatic Rule Refinement for Information Extraction. PVLDB, Vol. 3, 1 (2010)."},{"key":"e_1_3_2_2_21_1","volume-title":"Learning Word Vectors for Sentiment Analysis","author":"Maas Andrew L.","unstructured":"Andrew L. Maas, Raymond E. Daly, Peter T. Pham, Dan Huang, Andrew Y. Ng, and Christopher Potts. 2011. Learning Word Vectors for Sentiment Analysis. In Association for Computational Linguistics: Human Language Technologies, Dekang Lin, Yuji Matsumoto, and Rada Mihalcea(Eds.). 142-150."},{"key":"e_1_3_2_2_22_1","volume-title":"International Conference on Information Systems for Crisis Response and Management, Kees Boersma and Brian M. Tomaszewski(Eds.). ISCRAM Association.","author":"Mouzannar Hussein","year":"2018","unstructured":"Hussein Mouzannar, Yara Rizk, and Mariette Awad. 2018. Damage Identification in Social Media Posts using Multimodal Deep Learning. In International Conference on Information Systems for Crisis Response and Management, Kees Boersma and Brian M. Tomaszewski(Eds.). ISCRAM Association."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.12125"},{"key":"e_1_3_2_2_24_1","first-page":"354","article-title":"Towards Interactive Debugging of Rule-based Entity Matching","author":"Panahi Fatemah","year":"2017","unstructured":"Fatemah Panahi, Wentao Wu, AnHai Doan, and Jeffrey F Naughton. 2017. Towards Interactive Debugging of Rule-based Entity Matching.. In EDBT. 354-365.","journal-title":"EDBT."},{"key":"e_1_3_2_2_25_1","first-page":"2","article-title":"Snorkel: rapid training data creation with weak supervision","volume":"29","author":"Ratner Alexander","year":"2020","unstructured":"Alexander Ratner, Stephen H. Bach, Henry R. Ehrenberg, Jason A. Fries, Sen Wu, and Christopher R\u00e9. 2020. Snorkel: rapid training data creation with weak supervision. VLDBJ, Vol. 29, 2-3 (2020), 709-730.","journal-title":"VLDBJ"},{"key":"e_1_3_2_2_26_1","first-page":"3567","article-title":"Data Programming: Creating Large Training Sets, Quickly","author":"Ratner Alexander J.","year":"2016","unstructured":"Alexander J. Ratner, Christopher De Sa, Sen Wu, Daniel Selsam, and Christopher R\u00e9. 2016. Data Programming: Creating Large Training Sets, Quickly. In NIPS. 3567-3575.","journal-title":"NIPS."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.14778\/3137628.3137631"},{"key":"e_1_3_2_2_28_1","first-page":"457","article-title":"Provenance-based dictionary refinement in information extraction","author":"Roy Sudeepa","year":"2013","unstructured":"Sudeepa Roy, Laura Chiticariu, Vitaly Feldman, Frederick R Reiss, and Huaiyu Zhu. 2013. Provenance-based dictionary refinement in information extraction. In SIGMOD. 457-468.","journal-title":"SIGMOD."},{"key":"e_1_3_2_2_29_1","volume-title":"ULF: Unsupervised Labeling Function Correction using Cross-Validation for Weak Supervision. CoRR","author":"Sedova Anastasiya","year":"2022","unstructured":"Anastasiya Sedova and Benjamin Roth. 2022. ULF: Unsupervised Labeling Function Correction using Cross-Validation for Weak Supervision. CoRR, Vol. abs\/2204.06863 (2022)."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.14778\/3291264.3291268"},{"key":"e_1_3_2_2_31_1","first-page":"5153","article-title":"CrossWeigh: Training Named Entity Tagger from Imperfect Annotations","author":"Wang Zihan","year":"2019","unstructured":"Zihan Wang, Jingbo Shang, Liyuan Liu, Lihao Lu, Jiacheng Liu, and Jiawei Han. 2019. CrossWeigh: Training Named Entity Tagger from Imperfect Annotations. In EMNLP-IJCNLP. 5153-5162.","journal-title":"EMNLP-IJCNLP."},{"key":"e_1_3_2_2_32_1","volume-title":"Alfred: A System for Prompted Weak Supervision. arXiv preprint arXiv:2305.18623(2023).","author":"Yu Peilin","year":"2023","unstructured":"Peilin Yu and Stephen Bach. 2023. Alfred: A System for Prompted Weak Supervision. arXiv preprint arXiv:2305.18623(2023)."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"crossref","unstructured":"Yue Yu Simiao Zuo Haoming Jiang Wendi Ren Tuo Zhao and Chao Zhang. 2020. Fine-tuning pre-trained language model with weak supervision: A contrastive-regularized self-training approach. arXiv preprint arXiv:2010.07835(2020).","DOI":"10.18653\/v1\/2021.naacl-main.84"},{"key":"e_1_3_2_2_34_1","volume-title":"A Survey on Programmatic Weak Supervision. CoRR","author":"Zhang Jieyu","year":"2022","unstructured":"Jieyu Zhang, Cheng-Yu Hsieh, Yue Yu, Chao Zhang, and Alexander Ratner. 2022a. A Survey on Programmatic Weak Supervision. CoRR, Vol. abs\/2202.05433 (2022). arXiv:2202.05433"},{"key":"e_1_3_2_2_35_1","volume-title":"Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022","author":"Zhang Jieyu","year":"2022","unstructured":"Jieyu Zhang, Haonan Wang, Cheng-Yu Hsieh, and Alexander J. Ratner. 2022b. Understanding Programmatic Weak Supervision via Source-aware Influence Function. In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022."},{"key":"e_1_3_2_2_36_1","volume-title":"WRENCH: A comprehensive benchmark for weak supervision. arXiv preprint arXiv:2109.11377(2021).","author":"Zhang Jieyu","year":"2021","unstructured":"Jieyu Zhang, Yue Yu, Yinghao Li, Yujing Wang, Yaming Yang, Mao Yang, and Alexander Ratner. 2021. WRENCH: A comprehensive benchmark for weak supervision. arXiv preprint arXiv:2109.11377(2021)."},{"key":"e_1_3_2_2_37_1","volume-title":"LabelVizier: Interactive Validation and Relabeling for Technical Text Annotations. In 2023 IEEE 16th Pacific Visualization Symposium (PacificVis). IEEE, 167-176","author":"Zhang Xiaoyu","year":"2023","unstructured":"Xiaoyu Zhang, Xiwei Xuan, Alden Dima, Thurston Sexton, and Kwan-Liu Ma. 2023. LabelVizier: Interactive Validation and Relabeling for Technical Text Annotations. In 2023 IEEE 16th Pacific Visualization Symposium (PacificVis). IEEE, 167-176."},{"key":"e_1_3_2_2_38_1","volume-title":"Junbo Jake Zhao, and Yann LeCun","author":"Zhang Xiang","year":"2015","unstructured":"Xiang Zhang, Junbo Jake Zhao, and Yann LeCun. 2015. Character-level Convolutional Networks for Text Classification. In NeurIPS, Corinna Cortes, Neil D. Lawrence, Daniel D. Lee, Masashi Sugiyama, and Roman Garnett(Eds.). 649-657."}],"event":{"name":"KDD '25: The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Toronto ON Canada","acronym":"KDD '25","sponsor":["SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3711896.3737102","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T18:08:15Z","timestamp":1777572495000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3711896.3737102"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,3]]},"references-count":38,"alternative-id":["10.1145\/3711896.3737102","10.1145\/3711896"],"URL":"https:\/\/doi.org\/10.1145\/3711896.3737102","relation":{},"subject":[],"published":{"date-parts":[[2025,8,3]]},"assertion":[{"value":"2025-08-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}