{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,5]],"date-time":"2026-09-05T01:25:25Z","timestamp":1788571525564,"version":"build-2803163510"},"reference-count":75,"publisher":"Association for Computing Machinery (ACM)","issue":"10","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Proc. VLDB Endow."],"published-print":{"date-parts":[[2025,6]]},"abstract":"<jats:p>Missing data imputation, which aims to impute the missing values in the raw datasets, is crucial for modern data-driven models like large language models (LLMs). Despite its importance, existing solutions either 1) only support numerical and categorical data or 2) show an unsatisfactory performance due to their design prioritizing text data and overlooking intrinsic characteristics of tabular data.<\/jats:p>\n                  <jats:p>\n                    In this paper, we propose UnIMP, a\n                    <jats:bold>Un<\/jats:bold>\n                    ified\n                    <jats:bold>IMP<\/jats:bold>\n                    utation framework that leverages LLM and high-order message passing to enhance the imputation of mixed-type data, including numerical, categorical, and text data. Specifically, we first introduce a cell-oriented hypergraph to model the table. We then propose BiHMP, an efficient Bidirectional High-order Message-Passing network to aggregate global-local and high-order information while capturing the inter-column heterogeneity and intra-column homogeneity. To align the capacity of the LLM with the information aggregated by BiHMP, we introduce Xfusion, which, together with BiHMP, acts as adapters for the LLM. We follow a pre-training and fine-tuning pipeline to train UnIMP, integrating two optimizations: chunking technique, which divides tables into smaller chunks to enhance efficiency; and progressive masking technique, which gradually adapts the model to learn more complex data patterns. Both theoretical proofs and empirical experiments on 10 real-world datasets highlight the superiority of UnIMP over existing techniques.\n                  <\/jats:p>","DOI":"10.14778\/3748191.3748205","type":"journal-article","created":{"date-parts":[[2025,9,4]],"date-time":"2025-09-04T13:50:16Z","timestamp":1756993816000},"page":"3421-3434","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["On LLM-Enhanced Mixed-Type Data Imputation with High-Order Message Passing"],"prefix":"10.14778","volume":"18","author":[{"given":"Jianwei","family":"Wang","sequence":"first","affiliation":[{"name":"Schools of Computer Science and Engineering, University of New, South Wales"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Wang","sequence":"additional","affiliation":[{"name":"Antai College of Economics &amp; Management, Shanghai, Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Zhang","sequence":"additional","affiliation":[{"name":"Common Prosperity Visualization and Policy Simulation Lab, Zhejiang Gongshang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenjie","family":"Zhang","sequence":"additional","affiliation":[{"name":"Schools of Computer Science and Engineering, University of New, South Wales"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiwei","family":"Xu","sequence":"additional","affiliation":[{"name":"Data61, CSIRO"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuemin","family":"Lin","sequence":"additional","affiliation":[{"name":"Antai College of Economics &amp; Management, Shanghai, Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,9,4]]},"reference":[{"key":"e_1_2_1_1_1","unstructured":"2024. Mastering Mixed Methods Research in 2024: Combining Qualitative and Quantitative Approaches. https:\/\/editverse.com\/mastering-mixed-methods-research-in-2024\/"},{"key":"e_1_2_1_2_1","volume-title":"Data Science and Intelligent Systems: Proceedings of 5th Computational Methods in Systems and Software","volume":"2","author":"Alexandr Nikolich","year":"2021","unstructured":"Nikolich Alexandr, Osliakova Irina, Kudinova Tatyana, Kappusheva Inessa, and Puchkova Arina. 2021. Fine-tuning GPT-3 for Russian text summarization. In Data Science and Intelligent Systems: Proceedings of 5th Computational Methods in Systems and Software 2021, Vol. 2. Springer, 748\u2013757."},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1080\/00031305.1992.10475879"},{"key":"e_1_2_1_4_1","volume-title":"Formalizing BPE Tokenization. arXiv preprint arXiv:2309.08715","author":"Berglund Martin","year":"2023","unstructured":"Martin Berglund and Brink van der Merwe. 2023. Formalizing BPE Tokenization. arXiv preprint arXiv:2309.08715 (2023)."},{"key":"e_1_2_1_5_1","volume-title":"European Conference on Advances in Databases and Information Systems. Springer, 68\u201378","author":"Biester Fabian","year":"2024","unstructured":"Fabian Biester, Mohamed Abdelaal, and Daniel Del Gaudio. 2024. Llmclean: Context-aware tabular data cleaning via llm-generated ofds. In European Conference on Advances in Databases and Information Systems. Springer, 68\u201378."},{"key":"e_1_2_1_6_1","volume-title":"Language models are few-shot learners. arXiv preprint arXiv:2005.14165","author":"Brown Tom B","year":"2020","unstructured":"Tom B Brown. 2020. Language models are few-shot learners. arXiv preprint arXiv:2005.14165 (2020)."},{"key":"e_1_2_1_7_1","volume-title":"2023 IEEE 35th International Conference on Tools with Artificial Intelligence (ICTAI). IEEE, 723\u2013730","author":"Chen Katrina","year":"2023","unstructured":"Katrina Chen, Xiuqin Liang, Zheng Ma, and Zhibin Zhang. 2023. GEDI: A graph-based end-to-end data imputation framework. In 2023 IEEE 35th International Conference on Tools with Artificial Intelligence (ICTAI). IEEE, 723\u2013730."},{"key":"e_1_2_1_8_1","volume-title":"HYTREL: Hypergraphenhanced tabular data representation learning. Advances in Neural Information Processing Systems 36","author":"Chen Pei","year":"2024","unstructured":"Pei Chen, Soumajyoti Sarkar, Leonard Lausen, Balasubramaniam Srinivasan, Sheng Zha, Ruihong Huang, and George Karypis. 2024. HYTREL: Hypergraphenhanced tabular data representation learning. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-005-5724-z"},{"key":"e_1_2_1_11_1","volume-title":"Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies","volume":"1","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. In Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers). 4171\u20134186."},{"key":"e_1_2_1_12_1","first-page":"16373","article-title":"Learning enhanced representation for tabular data via neighborhood propagation","volume":"35","author":"Du Kounianhua","year":"2022","unstructured":"Kounianhua Du, Weinan Zhang, Ruiwen Zhou, Yangkun Wang, Xilong Zhao, Jiarui Jin, Quan Gan, Zheng Zhang, and David P Wipf. 2022. Learning enhanced representation for tabular data via neighborhood propagation. Advances in Neural Information Processing Systems 35 (2022), 16373\u201316384.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_13_1","volume-title":"ReMasker: Imputing Tabular Data with Masked Autoencoding. In The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Du Tianyu","year":"2024","unstructured":"Tianyu Du, Luca Melis, and Ting Wang. 2024. ReMasker: Imputing Tabular Data with Masked Autoencoding. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7\u201311, 2024. OpenReview.net. https:\/\/openreview.net\/forum?id=KI9NqjLVDT"},{"key":"e_1_2_1_14_1","unstructured":"Dheeru Dua and Casey Graff. 2017. UCI Machine Learning Repository. http:\/\/archive.ics.uci.edu\/ml"},{"key":"e_1_2_1_15_1","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_2_1_16_1","unstructured":"Jianwei Wang et al. 2025. UnIMP: Full Version. https:\/\/github.com\/guaiyoui\/UnIMP\/blob\/master\/full_version\/UnIMP_Full_Version.pdf. Accessed April 2025."},{"key":"e_1_2_1_17_1","unstructured":"Xi Fang Weijie Xu Fiona Anting Tan Ziqing Hu Jiani Zhang Yanjun Qi Srinivasan H Sengamedu and Christos Faloutsos. [n.d.]. Large Language Models (LLMs) on Tabular Data: Prediction Generation and Understanding-A Survey. Transactions on Machine Learning Research ([n. d.])."},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCA.2007.902631"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013558"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-009-0295-6"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-93040-4_21"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-020-00305-w"},{"key":"e_1_2_1_23_1","volume-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2208\u20132222","author":"He Ruidan","year":"2021","unstructured":"Ruidan He, Linlin Liu, Hai Ye, Qingyu Tan, Bosheng Ding, Liying Cheng, Jiawei Low, Lidong Bing, and Luo Si. 2021. On the Effectiveness of Adapter-based Tuning for Pretrained Language Model Adaptation. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2208\u20132222."},{"key":"e_1_2_1_24_1","volume-title":"Breakthroughs in statistics: Methodology and distribution","author":"Huber Peter J","unstructured":"Peter J Huber. 1992. Robust estimation of a location parameter. In Breakthroughs in statistics: Methodology and distribution. Springer, 492\u2013518."},{"key":"e_1_2_1_25_1","volume-title":"Handbook of latent variable and related models","author":"Jamshidian Mortaza","unstructured":"Mortaza Jamshidian and Matthew Mata. 2007. Advances in analysis of mean and covariance structure when data are incomplete. In Handbook of latent variable and related models. Elsevier, 21\u201344."},{"key":"e_1_2_1_26_1","volume-title":"Leo Anthony Celi, and Roger G Mark","author":"Johnson Alistair EW","year":"2016","unstructured":"Alistair EW Johnson, Tom J Pollard, Lu Shen, Li-wei H Lehman, Mengling Feng, Mohammad Ghassemi, Benjamin Moody, Peter Szolovits, Leo Anthony Celi, and Roger G Mark. 2016. MIMIC-III, a freely accessible critical care database. Scientific data 3, 1 (2016), 1\u20139."},{"key":"e_1_2_1_27_1","unstructured":"Kaggle. 2021. Flipkart Products. https:\/\/www.kaggle.com\/datasets\/PromptCloudHQ\/flipkart-products\/data"},{"key":"e_1_2_1_28_1","volume-title":"International Conference on Machine Learning. PMLR, 16049\u201316096","author":"Kawaguchi Kenji","year":"2023","unstructured":"Kenji Kawaguchi, Zhun Deng, Xu Ji, and Jiaoyang Huang. 2023. How does information bottleneck help deep learning?. In International Conference on Machine Learning. PMLR, 16049\u201316096."},{"key":"e_1_2_1_29_1","volume-title":"Sentencepiece: A simple and language independent subword tokenizer and detokenizer for neural text processing. arXiv preprint arXiv:1808.06226","author":"Kudo T","year":"2018","unstructured":"T Kudo. 2018. Sentencepiece: A simple and language independent subword tokenizer and detokenizer for neural text processing. arXiv preprint arXiv:1808.06226 (2018)."},{"key":"e_1_2_1_30_1","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","volume":"33","author":"Lewis Patrick","year":"2020","unstructured":"Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich K\u00fcttler, Mike Lewis, Wen-tau Yih, Tim Rockt\u00e4schel, et al. 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in Neural Information Processing Systems 33 (2020), 9459\u20139474.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3654979"},{"key":"e_1_2_1_32_1","volume-title":"2024 IEEE 40th International Conference on Data Engineering (ICDE). IEEE, 2503\u20132516","author":"Li Shunyang","year":"2024","unstructured":"Shunyang Li, Kai Wang, Xuemin Lin, Wenjie Zhang, Yizhang He, and Long Yuan. 2024. Querying Historical Cohesive Subgraphs over Temporal Bipartite Graphs. In 2024 IEEE 40th International Conference on Data Engineering (ICDE). IEEE, 2503\u20132516."},{"key":"e_1_2_1_33_1","volume-title":"Efficient Bitruss Decomposition on GPU","author":"Li Shunyang","year":"2025","unstructured":"Shunyang Li, Kai Wang, Wenjie Zhang, Xuemin Lin, and Yizhang He. 2025. Efficient Bitruss Decomposition on GPU. IEEE Transactions on Knowledge and Data Engineering (2025)."},{"key":"e_1_2_1_34_1","volume-title":"Label supervised llama finetuning. arXiv preprint arXiv:2310.01208","author":"Li Zongxi","year":"2023","unstructured":"Zongxi Li, Xianming Li, Yuzhang Liu, Haoran Xie, Jing Li, Fu-lee Wang, Qing Li, and Xiaoqin Zhong. 2023. Label supervised llama finetuning. arXiv preprint arXiv:2310.01208 (2023)."},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-019-09709-4"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.4236\/jcc.2015.35021"},{"key":"e_1_2_1_37_1","volume-title":"International conference on machine learning. PMLR, 4413\u20134423","author":"Mattei Pierre-Alexandre","year":"2019","unstructured":"Pierre-Alexandre Mattei and Jes Frellsen. 2019. MIWAE: Deep generative modelling and imputation of incomplete data sets. In International conference on machine learning. PMLR, 4413\u20134423."},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2018.09.406"},{"key":"e_1_2_1_39_1","volume-title":"2021 IEEE 37th International Conference on Data Engineering (ICDE). IEEE, 61\u201372","author":"Mei Yinan","year":"2021","unstructured":"Yinan Mei, Shaoxu Song, Chenguang Fang, Haifeng Yang, Jingyun Fang, and Jiang Long. 2021. Capturing semantics for imputation with pre-trained language models. In 2021 IEEE 37th International Conference on Data Engineering (ICDE). IEEE, 61\u201372."},{"key":"e_1_2_1_40_1","first-page":"6630","article-title":"An experimental survey of missing data imputation algorithms","volume":"35","author":"Miao Xiaoye","year":"2022","unstructured":"Xiaoye Miao, Yangyang Wu, Lu Chen, Yunjun Gao, and Jianwei Yin. 2022. An experimental survey of missing data imputation algorithms. IEEE Transactions on Knowledge and Data Engineering 35, 7 (2022), 6630\u20136650.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"e_1_2_1_41_1","unstructured":"Microsoft. 2024. microsoft\/phi-2. https:\/\/huggingface.co\/microsoft\/phi-2"},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2006.01.009"},{"key":"e_1_2_1_43_1","volume-title":"International Conference on Machine Learning. PMLR, 7130\u20137140","author":"Muzellec Boris","year":"2020","unstructured":"Boris Muzellec, Julie Josse, Claire Boyer, and Marco Cuturi. 2020. Missing data imputation using optimal transport. In International Conference on Machine Learning. PMLR, 7130\u20137140."},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/K16-1028"},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.14778\/3574245.3574258"},{"key":"e_1_2_1_46_1","first-page":"465","article-title":"UniDM: A Unified Framework for Data Manipulation with Large Language Models","volume":"6","author":"Qian Yichen","year":"2024","unstructured":"Yichen Qian, Yongyi He, Rong Zhu, Jintao Huang, Zhijian Ma, Haibin Wang, Yaohua Wang, Xiuyu Sun, Defu Lian, Bolin Ding, et al. 2024. UniDM: A Unified Framework for Data Manipulation with Large Language Models. Proceedings of Machine Learning and Systems 6 (2024), 465\u2013482.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/D19-1410"},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v045.i04"},{"key":"e_1_2_1_49_1","volume-title":"Embeddings for Tabular Data: A Survey. arXiv preprint arXiv:2302.11777","author":"Singh Rajat","year":"2023","unstructured":"Rajat Singh and Srikanta Bedathur. 2023. Embeddings for Tabular Data: A Survey. arXiv preprint arXiv:2302.11777 (2023)."},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.06.005"},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btr597"},{"key":"e_1_2_1_52_1","unstructured":"Bohan Tang Zexi Liu Keyue Jiang Siheng Chen and Xiaowen Dong. 2024. Simplifying Hypergraph Neural Networks. https:\/\/api.semanticscholar.org\/CorpusID:267547514"},{"key":"e_1_2_1_53_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_2_1_54_1","volume-title":"Attention is all you need. Advances in Neural Information Processing Systems","author":"Vaswani A","year":"2017","unstructured":"A Vaswani. 2017. Attention is all you need. Advances in Neural Information Processing Systems (2017)."},{"key":"e_1_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.14778\/3665844.3665853"},{"key":"e_1_2_1_56_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3626738","article-title":"Neural Attributed Community Search at Billion Scale","volume":"1","author":"Wang Jianwei","year":"2024","unstructured":"Jianwei Wang, Kai Wang, Xuemin Lin, Wenjie Zhang, and Ying Zhang. 2024. Neural Attributed Community Search at Billion Scale. Proceedings of the ACM on Management of Data 1, 4 (2024), 1\u201325.","journal-title":"Proceedings of the ACM on Management of Data"},{"key":"e_1_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3654920"},{"key":"e_1_2_1_58_1","volume-title":"ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 4058\u20134062","author":"Wang Wei","year":"2022","unstructured":"Wei Wang, Yimeng Chai, and Yue Li. 2022. A Global to Local Guiding Network for Missing Data Imputation. In ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 4058\u20134062."},{"key":"e_1_2_1_59_1","volume-title":"The growing importance of mixed-methods research in health. Nepal journal of epidemiology 12, 1","author":"Wasti Sharada Prasad","year":"2022","unstructured":"Sharada Prasad Wasti, Padam Simkhada, Edwin R van Teijlingen, Brijesh Sathian, and Indrajit Banerjee. 2022. The growing importance of mixed-methods research in health. Nepal journal of epidemiology 12, 1 (2022), 1175."},{"key":"e_1_2_1_60_1","volume-title":"Multiple imputation using chained equations: issues and guidance for practice. Statistics in medicine 30, 4","author":"White Ian R","year":"2011","unstructured":"Ian R White, Patrick Royston, and Angela M Wood. 2011. Multiple imputation using chained equations: issues and guidance for practice. Statistics in medicine 30, 4 (2011), 377\u2013399."},{"key":"e_1_2_1_61_1","volume-title":"The Free Encyclopedia. https:\/\/en.wikipedia.org\/w\/index.php?title=Information_bottleneck_method&oldid=1260066467 [Online","author":"Wikipedia","year":"2024","unstructured":"Wikipedia contributors. 2024. Information bottleneck method \u2014 Wikipedia, The Free Encyclopedia. https:\/\/en.wikipedia.org\/w\/index.php?title=Information_bottleneck_method&oldid=1260066467 [Online; accessed 8-December-2024]."},{"key":"e_1_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3387439"},{"key":"e_1_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3293129"},{"key":"e_1_2_1_64_1","volume-title":"Xia Ben Hu","author":"Han Xiaotian","year":"2024","unstructured":"Xiaotian Han, Xia Ben Hu. 2024. ahxt\/LiteLlama-460M-1T. https:\/\/huggingface.co\/ahxt\/LiteLlama-460M-1T"},{"key":"e_1_2_1_65_1","unstructured":"Shuangyin Xie. 2019. Sentiment Analysis using machine learning algorithms: online women clothing reviews. Ph.D. Dissertation. Dublin National College of Ireland."},{"key":"e_1_2_1_66_1","volume-title":"Proceedings of the 21th ACM SIGKDD international conference on knowledge discovery and data mining. 1395\u20131404","author":"Yang Yang","year":"2015","unstructured":"Yang Yang, Yizhou Sun, Jie Tang, Bo Ma, and Juanzi Li. 2015. Entity matching across heterogeneous sources. In Proceedings of the 21th ACM SIGKDD international conference on knowledge discovery and data mining. 1395\u20131404."},{"key":"e_1_2_1_67_1","volume-title":"Financial Report Chunking for Effective Retrieval Augmented Generation. arXiv preprint arXiv:2402.05131","author":"Yepes Antonio Jimeno","year":"2024","unstructured":"Antonio Jimeno Yepes, Yao You, Jan Milczek, Sebastian Laverde, and Leah Li. 2024. Financial Report Chunking for Effective Retrieval Augmented Generation. arXiv preprint arXiv:2402.05131 (2024)."},{"key":"e_1_2_1_68_1","volume-title":"International conference on machine learning. PMLR, 5689\u20135698","author":"Yoon Jinsung","year":"2018","unstructured":"Jinsung Yoon, James Jordon, and Mihaela Schaar. 2018. Gain: Missing data imputation using generative adversarial nets. In International conference on machine learning. PMLR, 5689\u20135698."},{"key":"e_1_2_1_69_1","first-page":"19075","article-title":"Handling missing data with graph representation learning","volume":"33","author":"You Jiaxuan","year":"2020","unstructured":"Jiaxuan You, Xiaobai Ma, Yi Ding, Mykel J Kochenderfer, and Jure Leskovec. 2020. Handling missing data with graph representation learning. Advances in Neural Information Processing Systems 33 (2020), 19075\u201319087.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_70_1","volume-title":"Large language models as data preprocessors. arXiv preprint arXiv:2308.16361","author":"Zhang Haochen","year":"2023","unstructured":"Haochen Zhang, Yuyang Dong, Chuan Xiao, and Masafumi Oyamada. 2023. Large language models as data preprocessors. arXiv preprint arXiv:2308.16361 (2023)."},{"key":"e_1_2_1_71_1","volume-title":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 8754\u20138782","author":"Zhang Haochen","year":"2024","unstructured":"Haochen Zhang, Yuyang Dong, Chuan Xiao, and Masafumi Oyamada. 2024. Jellyfish: Instruction-Tuning Local Large Language Models for Data Preprocessing. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 8754\u20138782."},{"key":"e_1_2_1_72_1","volume-title":"Llama-adapter: Efficient fine-tuning of language models with zero-init attention. arXiv preprint arXiv:2303.16199","author":"Zhang Renrui","year":"2023","unstructured":"Renrui Zhang, Jiaming Han, Chris Liu, Peng Gao, Aojun Zhou, Xiangfei Hu, Shilin Yan, Pan Lu, Hongsheng Li, and Yu Qiao. 2023. Llama-adapter: Efficient fine-tuning of language models with zero-init attention. arXiv preprint arXiv:2303.16199 (2023)."},{"key":"e_1_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2012.05.073"},{"key":"e_1_2_1_74_1","volume-title":"International Conference on Machine Learning. PMLR, 42159\u201342186","author":"Zhao He","year":"2023","unstructured":"He Zhao, Ke Sun, Amir Dezfouli, and Edwin V Bonilla. 2023. Transformed distribution matching for missing value imputation. In International Conference on Machine Learning. PMLR, 42159\u201342186."},{"key":"e_1_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26348"}],"container-title":["Proceedings of the VLDB Endowment"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.14778\/3748191.3748205","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,4]],"date-time":"2025-09-04T13:54:07Z","timestamp":1756994047000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.14778\/3748191.3748205"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":75,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["10.14778\/3748191.3748205"],"URL":"https:\/\/doi.org\/10.14778\/3748191.3748205","relation":{},"ISSN":["2150-8097"],"issn-type":[{"value":"2150-8097","type":"print"}],"subject":[],"published":{"date-parts":[[2025,6]]},"assertion":[{"value":"2025-09-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}