{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T16:48:00Z","timestamp":1755794880942,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":68,"publisher":"ACM","funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["IIS-2008334, IIS-2106961, IIS-2403240, and CAREER IIS-2144338"],"award-info":[{"award-number":["IIS-2008334, IIS-2106961, IIS-2403240, and CAREER IIS-2144338"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/100000001","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\/3711896.3736871","type":"proceedings-article","created":{"date-parts":[[2025,8,3]],"date-time":"2025-08-03T20:54:17Z","timestamp":1754254457000},"page":"3598-3609","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Calibrating Pre-trained Language Classifiers on LLM-generated Noisy Labels via Iterative Refinement"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-0390-8802","authenticated-orcid":false,"given":"Liqin","family":"Ye","sequence":"first","affiliation":[{"name":"School of Computational Science & Engineering, Georgia Institute of Technology, Atlanta, Georgia, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9062-2430","authenticated-orcid":false,"given":"Agam","family":"Shah","sequence":"additional","affiliation":[{"name":"School of Computational Science & Engineering, Georgia Institute of Technology, Atlanta, Georgia, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3009-598X","authenticated-orcid":false,"given":"Chao","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computational Science & Engineering, Georgia Institute of Technology, Atlanta, Georgia, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8330-682X","authenticated-orcid":false,"given":"Sudheer","family":"Chava","sequence":"additional","affiliation":[{"name":"Scheller College of Business, Georgia Institute of Technology, Atlanta, Georgia, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,8,3]]},"reference":[{"unstructured":"Eric Arazo Diego Ortego Paul Albert Noel E. O'Connor and Kevin McGuinness. 2019. Unsupervised Label Noise Modeling and Loss Correction. arXiv:1904.11238 [cs.CV] https:\/\/arxiv.org\/abs\/1904.11238","key":"e_1_3_2_2_1_1"},{"unstructured":"Devansh Arpit Stanislaw Jastrzebski Nicolas Ballas David Krueger Emmanuel Bengio Maxinder S. Kanwal Tegan Maharaj Asja Fischer Aaron Courville Yoshua Bengio and Simon Lacoste-Julien. 2017. A Closer Look at Memorization in Deep Networks. arXiv:1706.05394 [stat.ML] https:\/\/arxiv.org\/abs\/1706.05394","key":"e_1_3_2_2_2_1"},{"key":"e_1_3_2_2_3_1","volume-title":"International Conference on Machine Learning. PMLR, 1277-1297","author":"Bae HeeSun","year":"2022","unstructured":"HeeSun Bae, Seungjae Shin, Byeonghu Na, JoonHo Jang, Kyungwoo Song, and Il-Chul Moon. 2022. From noisy prediction to true label: Noisy prediction calibration via generative model. In International Conference on Machine Learning. PMLR, 1277-1297."},{"unstructured":"Antonin Berthon Bo Han Gang Niu Tongliang Liu and Masashi Sugiyama. 2021. Confidence Scores Make Instance-dependent Label-noise Learning Possible. arXiv:2001.03772 [cs.LG]","key":"e_1_3_2_2_4_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_5_1","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"e_1_3_2_2_6_1","volume-title":"Brown et al","author":"Tom","year":"2020","unstructured":"Tom B. Brown et al., 2020. Language Models are Few-Shot Learners. arXiv:2005.14165 [cs.CL] https:\/\/arxiv.org\/abs\/2005.14165"},{"key":"e_1_3_2_2_7_1","volume-title":"Bowen Baker, Leo Gao, Leopold Aschenbrenner, Yining Chen, Adrien Ecoffet, Manas Joglekar, Jan Leike, Ilya Sutskever, and Jeff Wu.","author":"Burns Collin","year":"2023","unstructured":"Collin Burns, Pavel Izmailov, Jan Hendrik Kirchner, Bowen Baker, Leo Gao, Leopold Aschenbrenner, Yining Chen, Adrien Ecoffet, Manas Joglekar, Jan Leike, Ilya Sutskever, and Jeff Wu. 2023. Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision. arXiv:2312.09390 [cs.CL] https:\/\/arxiv.org\/abs\/2312.09390"},{"unstructured":"Jian Chen Ruiyi Zhang Tong Yu Rohan Sharma Zhiqiang Xu Tong Sun and Changyou Chen. 2023a. Label-Retrieval-Augmented Diffusion Models for Learning from Noisy Labels. arXiv:2305.19518 [cs.LG] https:\/\/arxiv.org\/abs\/2305.19518","key":"e_1_3_2_2_8_1"},{"unstructured":"Jian Chen Ruiyi Zhang Tong Yu Rohan Sharma Zhiqiang Xu Tong Sun and Changyou Chen. 2023b. Label-Retrieval-Augmented Diffusion Models for Learning from Noisy Labels. arXiv:2305.19518 [cs.LG]","key":"e_1_3_2_2_9_1"},{"unstructured":"Hao Cheng Zhaowei Zhu Xingyu Li Yifei Gong Xing Sun and Yang Liu. 2021. Learning with Instance-Dependent Label Noise: A Sample Sieve Approach. arXiv:2010.02347 [cs.LG] https:\/\/arxiv.org\/abs\/2010.02347","key":"e_1_3_2_2_10_1"},{"key":"e_1_3_2_2_11_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arXiv:1810.04805 [cs.CL] https:\/\/arxiv.org\/abs\/1810.04805","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arXiv:1810.04805 [cs.CL] https:\/\/arxiv.org\/abs\/1810.04805"},{"unstructured":"Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Amy Yang Angela Fan et al. 2024. The llama 3 herd of models. arXiv preprint arXiv:2407.21783(2024).","key":"e_1_3_2_2_12_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_13_1","DOI":"10.1073\/pnas.2305016120"},{"key":"e_1_3_2_2_14_1","volume-title":"Hodas","author":"Goh Garrett B.","year":"2018","unstructured":"Garrett B. Goh, Charles Siegel, Abhinav Vishnu, and Nathan O. Hodas. 2018. Using Rule-Based Labels for Weak Supervised Learning: A ChemNet for Transferable Chemical Property Prediction. arXiv:1712.02734 [stat.ML] https:\/\/arxiv.org\/abs\/1712.02734"},{"key":"e_1_3_2_2_15_1","volume-title":"Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels. arXiv:1804.06872 [cs.LG]","author":"Han Bo","year":"2018","unstructured":"Bo Han, Quanming Yao, Xingrui Yu, Gang Niu, Miao Xu, Weihua Hu, Ivor Tsang, and Masashi Sugiyama. 2018a. Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels. arXiv:1804.06872 [cs.LG]"},{"key":"e_1_3_2_2_16_1","volume-title":"Co-teaching: Robust training of deep neural networks with extremely noisy labels. Advances in neural information processing systems","author":"Han Bo","year":"2018","unstructured":"Bo Han, Quanming Yao, Xingrui Yu, Gang Niu, Miao Xu, Weihua Hu, Ivor Tsang, and Masashi Sugiyama. 2018b. Co-teaching: Robust training of deep neural networks with extremely noisy labels. Advances in neural information processing systems, Vol. 31 (2018)."},{"key":"e_1_3_2_2_17_1","volume-title":"CARD: Classification and Regression Diffusion Models. arXiv:2206.07275 [stat.ML]","author":"Han Xizewen","year":"2022","unstructured":"Xizewen Han, Huangjie Zheng, and Mingyuan Zhou. 2022. CARD: Classification and Regression Diffusion Models. arXiv:2206.07275 [stat.ML]"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_18_1","DOI":"10.1109\/bigdata62323.2024.10826001"},{"key":"e_1_3_2_2_19_1","volume-title":"Zornitsa Kozareva, Preslav Nakov, Diarmuid O S\u00e9aghdha, Sebastian Pad\u00f3, Marco Pennacchiotti, Lorenza Romano, and Stan Szpakowicz.","author":"Hendrickx Iris","year":"2019","unstructured":"Iris Hendrickx, Su Nam Kim, Zornitsa Kozareva, Preslav Nakov, Diarmuid O S\u00e9aghdha, Sebastian Pad\u00f3, Marco Pennacchiotti, Lorenza Romano, and Stan Szpakowicz. 2019. Semeval-2010 task 8: Multi-way classification of semantic relations between pairs of nominals. arXiv preprint arXiv:1911.10422(2019)."},{"doi-asserted-by":"crossref","unstructured":"Ahmet Iscen Jack Valmadre Anurag Arnab and Cordelia Schmid. 2022. Learning with Neighbor Consistency for Noisy Labels. arXiv:2202.02200 [cs.CV]","key":"e_1_3_2_2_20_1","DOI":"10.1109\/CVPR52688.2022.00463"},{"key":"e_1_3_2_2_21_1","volume-title":"Jiang et al","author":"Albert","year":"2024","unstructured":"Albert Q. Jiang et al., 2024. Mixtral of Experts. arXiv:2401.04088 [cs.LG]"},{"unstructured":"Weonyoung Joo Wonsung Lee Sungrae Park and Il-Chul Moon. 2019. Dirichlet Variational Autoencoder. arXiv:1901.02739 [cs.LG] https:\/\/arxiv.org\/abs\/1901.02739","key":"e_1_3_2_2_22_1"},{"key":"e_1_3_2_2_23_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2017","unstructured":"Diederik P. Kingma and Jimmy Ba. 2017. Adam: A Method for Stochastic Optimization. arXiv:1412.6980 [cs.LG]"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_24_1","DOI":"10.1016\/B978-1-55860-377-6.50048-7"},{"unstructured":"Xintong Li Jinya Jiang Ria Dharmani Jayanth Srinivasa Gaowen Liu and Jingbo Shang. 2024. Open-world Multi-label Text Classification with Extremely Weak Supervision. arXiv:2407.05609 [cs.CL] https:\/\/arxiv.org\/abs\/2407.05609","key":"e_1_3_2_2_25_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_26_1","DOI":"10.3115\/1072228.1072378"},{"unstructured":"Zhuoyan Li Hangxiao Zhu Zhuoran Lu and Ming Yin. 2023. Synthetic Data Generation with Large Language Models for Text Classification: Potential and Limitations. arXiv:2310.07849 [cs.CL] https:\/\/arxiv.org\/abs\/2310.07849","key":"e_1_3_2_2_27_1"},{"key":"e_1_3_2_2_28_1","volume-title":"TESS: Text-to-Text Self-Conditioned Simplex Diffusion. arXiv:2305.08379 [cs.CL]","author":"Mahabadi Rabeeh Karimi","year":"2024","unstructured":"Rabeeh Karimi Mahabadi, Hamish Ivison, Jaesung Tae, James Henderson, Iz Beltagy, Matthew E. Peters, and Arman Cohan. 2024. TESS: Text-to-Text Self-Conditioned Simplex Diffusion. arXiv:2305.08379 [cs.CL]"},{"unstructured":"Luca Moschella Valentino Maiorca Marco Fumero Antonio Norelli Francesco Locatello and Emanuele Rodol\u00e0. 2023. Relative representations enable zero-shot latent space communication. arXiv:2209.15430 [cs.LG] https:\/\/arxiv.org\/abs\/2209.15430","key":"e_1_3_2_2_29_1"},{"key":"e_1_3_2_2_30_1","volume-title":"Thi Phuong Nhung Ngo, Thi Hoai Phuong Nguyen, Laura Beggel, and Thomas Brox.","author":"Nguyen Duc Tam","year":"2019","unstructured":"Duc Tam Nguyen, Chaithanya Kumar Mummadi, Thi Phuong Nhung Ngo, Thi Hoai Phuong Nguyen, Laura Beggel, and Thomas Brox. 2019. SELF: Learning to Filter Noisy Labels with Self-Ensembling. arXiv:1910.01842 [cs.CV] https:\/\/arxiv.org\/abs\/1910.01842"},{"doi-asserted-by":"crossref","unstructured":"Vitor Oliveira Gabriel Nogueira Thiago Faleiros and Ricardo Marcacini. 2024. Combining prompt-based language models and weak supervision for labeling named entity recognition on legal documents. Artificial Intelligence and Law(2024) 1-21.","key":"e_1_3_2_2_31_1","DOI":"10.1007\/s10506-023-09388-1"},{"unstructured":"OpenAI et al. 2024. GPT-4 Technical Report. arXiv:2303.08774 [cs.CL] https:\/\/arxiv.org\/abs\/2303.08774","key":"e_1_3_2_2_32_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_33_1","DOI":"10.1109\/CVPR46437.2021.00654"},{"key":"e_1_3_2_2_34_1","volume-title":"PyTorch: An Imperative Style","author":"Paszke Adam","year":"1912","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas K\u00f6pf, Edward Yang, Zach DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019. PyTorch: An Imperative Style, High-Performance Deep Learning Library. arXiv:1912.01703 [cs.LG] https:\/\/arxiv.org\/abs\/1912.01703"},{"doi-asserted-by":"crossref","unstructured":"Giorgio Patrini Alessandro Rozza Aditya Menon Richard Nock and Lizhen Qu. 2017. Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach. arXiv:1609.03683 [stat.ML]","key":"e_1_3_2_2_35_1","DOI":"10.1109\/CVPR.2017.240"},{"unstructured":"Chengwei Qin Aston Zhang Zhuosheng Zhang Jiaao Chen Michihiro Yasunaga and Diyi Yang. 2023. Is ChatGPT a General-Purpose Natural Language Processing Task Solver? arXiv:2302.06476 [cs.CL] https:\/\/arxiv.org\/abs\/2302.06476","key":"e_1_3_2_2_36_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_37_1","DOI":"10.14778\/3157794.3157797"},{"key":"e_1_3_2_2_38_1","volume-title":"Chandra Bhagavatula, and Yejin Choi.","author":"Sakaguchi Keisuke","year":"2019","unstructured":"Keisuke Sakaguchi, Ronan Le Bras, Chandra Bhagavatula, and Yejin Choi. 2019. WinoGrande: An Adversarial Winograd Schema Challenge at Scale. arXiv:1907.10641 [cs.CL] https:\/\/arxiv.org\/abs\/1907.10641"},{"doi-asserted-by":"crossref","unstructured":"Agam Shah and Sudheer Chava. 2023. Zero is Not Hero Yet: Benchmarking Zero-Shot Performance of LLMs for Financial Tasks. arXiv:2305.16633 [cs.CL] https:\/\/arxiv.org\/abs\/2305.16633","key":"e_1_3_2_2_39_1","DOI":"10.2139\/ssrn.4458613"},{"doi-asserted-by":"crossref","unstructured":"Agam Shah Arnav Hiray Pratvi Shah Arkaprabha Banerjee Anushka Singh Dheeraj Eidnani Bhaskar Chaudhury and Sudheer Chava. 2024. Numerical Claim Detection in Finance: A New Financial Dataset Weak-Supervision Model and Market Analysis. arXiv preprint arXiv:2402.11728(2024).","key":"e_1_3_2_2_40_1","DOI":"10.18653\/v1\/2024.fever-1.21"},{"unstructured":"Team Snorkel. [n.d.]. Using few-shot learning language models as weak supervision - snorkel.ai. https:\/\/snorkel.ai\/blog\/few-shot-learning-large-language-models\/. [Accessed 07-02-2025].","key":"e_1_3_2_2_41_1"},{"unstructured":"Jascha Sohl-Dickstein Eric A. Weiss Niru Maheswaranathan and Surya Ganguli. 2015. Deep Unsupervised Learning using Nonequilibrium Thermodynamics. arXiv:1503.03585 [cs.LG]","key":"e_1_3_2_2_42_1"},{"doi-asserted-by":"crossref","unstructured":"Zhen Tan Dawei Li Song Wang Alimohammad Beigi Bohan Jiang Amrita Bhattacharjee Mansooreh Karami Jundong Li Lu Cheng and Huan Liu. 2024. Large Language Models for Data Annotation: A Survey. arXiv:2402.13446 [cs.CL] https:\/\/arxiv.org\/abs\/2402.13446","key":"e_1_3_2_2_43_1","DOI":"10.18653\/v1\/2024.emnlp-main.54"},{"unstructured":"Ke Wang Jiahui Zhu Minjie Ren Zeming Liu Shiwei Li Zongye Zhang Chenkai Zhang Xiaoyu Wu Qiqi Zhan Qingjie Liu and Yunhong Wang. 2024. A Survey on Data Synthesis and Augmentation for Large Language Models. arXiv:2410.12896 [cs.CL] https:\/\/arxiv.org\/abs\/2410.12896","key":"e_1_3_2_2_44_1"},{"unstructured":"Lei Wang Yi Hu Jiabang He Xing Xu Ning Liu Hui Liu and Heng Tao Shen. 2023a. T-SciQ: Teaching Multimodal Chain-of-Thought Reasoning via Mixed Large Language Model Signals for Science Question Answering. arXiv:2305.03453 [cs.CL] https:\/\/arxiv.org\/abs\/2305.03453","key":"e_1_3_2_2_45_1"},{"doi-asserted-by":"crossref","unstructured":"Song Wang Zhen Tan Ruocheng Guo and Jundong Li. 2023b. Noise-Robust Fine-Tuning of Pretrained Language Models via External Guidance. arXiv:2311.01108 [cs.CL] https:\/\/arxiv.org\/abs\/2311.01108","key":"e_1_3_2_2_46_1","DOI":"10.18653\/v1\/2023.findings-emnlp.834"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_47_1","DOI":"10.1109\/CVPR42600.2020.01374"},{"unstructured":"Jiaheng Wei Zhaowei Zhu Hao Cheng Tongliang Liu Gang Niu and Yang Liu. 2022. Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations. arXiv:2110.12088 [cs.LG] https:\/\/arxiv.org\/abs\/2110.12088","key":"e_1_3_2_2_48_1"},{"key":"e_1_3_2_2_49_1","volume-title":"Bowman","author":"Williams Adina","year":"2018","unstructured":"Adina Williams, Nikita Nangia, and Samuel R. Bowman. 2018. A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference. arXiv:1704.05426 [cs.CL] https:\/\/arxiv.org\/abs\/1704.05426"},{"unstructured":"Thomas Wolf et al. 2020. HuggingFace's Transformers: State-of-the-art Natural Language Processing. arXiv:1910.03771 [cs.CL] https:\/\/arxiv.org\/abs\/1910.03771","key":"e_1_3_2_2_50_1"},{"unstructured":"Xiaobo Xia Tongliang Liu Bo Han Nannan Wang Mingming Gong Haifeng Liu Gang Niu Dacheng Tao and Masashi Sugiyama. 2020a. Part-dependent Label Noise: Towards Instance-dependent Label Noise. arXiv:2006.07836 [cs.LG] https:\/\/arxiv.org\/abs\/2006.07836","key":"e_1_3_2_2_51_1"},{"unstructured":"Xiaobo Xia Tongliang Liu Bo Han Nannan Wang Mingming Gong Haifeng Liu Gang Niu Dacheng Tao and Masashi Sugiyama. 2020b. Part-dependent Label Noise: Towards Instance-dependent Label Noise. arXiv:2006.07836 [cs.LG]","key":"e_1_3_2_2_52_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_53_1","DOI":"10.1109\/CVPR.2015.7298885"},{"unstructured":"Yu Yao Tongliang Liu Mingming Gong Bo Han Gang Niu and Kun Zhang. 2022. Instance-dependent Label-noise Learning under a Structural Causal Model. arXiv:2109.02986 [stat.ML] https:\/\/arxiv.org\/abs\/2109.02986","key":"e_1_3_2_2_54_1"},{"unstructured":"Yu Yao Tongliang Liu Bo Han Mingming Gong Jiankang Deng Gang Niu and Masashi Sugiyama. 2021. Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learning. arXiv:2006.07805 [cs.LG]","key":"e_1_3_2_2_55_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_56_1","DOI":"10.18653\/v1\/2023.acl-demo.46"},{"unstructured":"Xingrui Yu Bo Han Jiangchao Yao Gang Niu Ivor W. Tsang and Masashi Sugiyama. 2019. How does Disagreement Help Generalization against Label Corruption? arXiv:1901.04215 [cs.LG] https:\/\/arxiv.org\/abs\/1901.04215","key":"e_1_3_2_2_57_1"},{"key":"e_1_3_2_2_58_1","volume-title":"Jialu Liu, Chao Zhang, and Michael Bendersky.","author":"Yu Yue","year":"2023","unstructured":"Yue Yu, Jiaming Shen, Tianqi Liu, Zhen Qin, Jing Nathan Yan, Jialu Liu, Chao Zhang, and Michael Bendersky. 2023. Explanation-aware soft ensemble empowers large language model in-context learning. arXiv preprint arXiv:2311.07099(2023)."},{"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).","key":"e_1_3_2_2_59_1","DOI":"10.18653\/v1\/2021.naacl-main.84"},{"key":"e_1_3_2_2_60_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. 2021c. Wrench: A comprehensive benchmark for weak supervision. arXiv preprint arXiv:2109.11377(2021)."},{"doi-asserted-by":"crossref","unstructured":"Rongzhi Zhang Yue Yu Pranav Shetty Le Song and Chao Zhang. 2022. PRBoost: Prompt-Based Rule Discovery and Boosting for Interactive Weakly-Supervised Learning. arXiv preprint arXiv:2203.09735(2022).","key":"e_1_3_2_2_61_1","DOI":"10.18653\/v1\/2022.acl-long.55"},{"unstructured":"Yivan Zhang Gang Niu and Masashi Sugiyama. 2021a. Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularization. arXiv:2102.02414 [stat.ML] https:\/\/arxiv.org\/abs\/2102.02414","key":"e_1_3_2_2_62_1"},{"unstructured":"Yivan Zhang Gang Niu and Masashi Sugiyama. 2021b. Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularization. arXiv:2102.02414 [stat.ML]","key":"e_1_3_2_2_63_1"},{"key":"e_1_3_2_2_64_1","volume-title":"Sabuncu","author":"Zhang Zhilu","year":"2018","unstructured":"Zhilu Zhang and Mert R. Sabuncu. 2018. Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels. arXiv:1805.07836 [cs.LG] https:\/\/arxiv.org\/abs\/1805.07836"},{"key":"e_1_3_2_2_65_1","volume-title":"A brief introduction to weakly supervised learning. National science review","author":"Zhou Zhi-Hua","year":"2018","unstructured":"Zhi-Hua Zhou. 2018. A brief introduction to weakly supervised learning. National science review, Vol. 5, 1 (2018), 44-53."},{"doi-asserted-by":"crossref","unstructured":"Dawei Zhu Xiaoyu Shen Marius Mosbach Andreas Stephan and Dietrich Klakow. 2023a. Weaker Than You Think: A Critical Look at Weakly Supervised Learning. arXiv:2305.17442 [cs.CL] https:\/\/arxiv.org\/abs\/2305.17442","key":"e_1_3_2_2_66_1","DOI":"10.18653\/v1\/2023.acl-long.796"},{"unstructured":"Yiming Zhu Peixian Zhang Ehsan-Ul Haq Pan Hui and Gareth Tyson. 2023b. Can ChatGPT Reproduce Human-Generated Labels? A Study of Social Computing Tasks. arXiv:2304.10145 [cs.AI] https:\/\/arxiv.org\/abs\/2304.10145","key":"e_1_3_2_2_67_1"},{"doi-asserted-by":"crossref","unstructured":"Yuchen Zhuang Yue Yu Lingkai Kong Xiang Chen and Chao Zhang. 2023. DyGen: Learning from Noisy Labels via Dynamics-Enhanced Generative Modeling. arXiv preprint arXiv:2305.19395(2023).","key":"e_1_3_2_2_68_1","DOI":"10.1145\/3580305.3599318"}],"event":{"sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"],"acronym":"KDD '25","name":"KDD '25: The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Toronto ON Canada"},"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\/3711896.3736871","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,16]],"date-time":"2025-08-16T14:34:46Z","timestamp":1755354886000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3711896.3736871"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,3]]},"references-count":68,"alternative-id":["10.1145\/3711896.3736871","10.1145\/3711896"],"URL":"https:\/\/doi.org\/10.1145\/3711896.3736871","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"}}]}}