{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:40:30Z","timestamp":1786120830429,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T00:00:00Z","timestamp":1786147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Postdoctoral Fellowship Program of CPSF","award":["GZB20250951"],"award-info":[{"award-number":["GZB20250951"]}]},{"name":"National Natural Science Foundation of China","award":["No. U2433212"],"award-info":[{"award-number":["No. U2433212"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770855.3817781","type":"proceedings-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T17:15:37Z","timestamp":1786036537000},"page":"2366-2376","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["inversedMixup: Data Augmentation via Inverting Mixed Embeddings"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9046-740X","authenticated-orcid":false,"given":"Fanshuang","family":"Kong","sequence":"first","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1207-0300","authenticated-orcid":false,"given":"Richong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4146-4765","authenticated-orcid":false,"given":"Qiyu","family":"Sun","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3933-0522","authenticated-orcid":false,"given":"Zhijie","family":"Nie","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8286-1014","authenticated-orcid":false,"given":"Ting","family":"Deng","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3473-9703","authenticated-orcid":false,"given":"Chunming","family":"Hu","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Nicholas Carlini Florian Tramer Eric Wallace Matthew Jagielski Ariel Herbert-Voss Katherine Lee Adam Roberts Tom Brown Dawn Song Ulfar Erlingsson et al. 2021. Extracting training data from large language models. In 30th USENIX security symposium (USENIX Security 21). 2633-2650."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.194"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26486"},{"key":"e_1_3_2_1_4_1","volume-title":"Text embedding inversion security for multilingual language models. arXiv preprint arXiv:2401.12192","author":"Chen Yiyi","year":"2024","unstructured":"Yiyi Chen, Heather Lent, and Johannes Bjerva. 2024. Text embedding inversion security for multilingual language models. arXiv preprint arXiv:2401.12192 (2024)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.409"},{"key":"e_1_3_2_1_6_1","first-page":"4171","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). 4171-4186."},{"key":"e_1_3_2_1_7_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 e-prints (2024) arXiv-2407."},{"key":"e_1_3_2_1_8_1","volume-title":"Self-Guided Noise-Free Data Generation for Efficient Zero-Shot Learning. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=h5OpjGd_lo6","author":"Gao Jiahui","year":"2023","unstructured":"Jiahui Gao, Renjie Pi, LIN Yong, Hang Xu, Jiacheng Ye, Zhiyong Wu, WEIZHONG ZHANG, Xiaodan Liang, Zhenguo Li, and Lingpeng Kong. 2023. Self-Guided Noise-Free Data Generation for Efficient Zero-Shot Learning. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=h5OpjGd_lo6"},{"key":"e_1_3_2_1_9_1","unstructured":"Jiawei Gu Xuhui Jiang Zhichao Shi Hexiang Tan Xuehao Zhai Chengjin Xu Wei Li Yinghan Shen Shengjie Ma Honghao Liu et al. 2024. A survey on llm-as-a-judge. arXiv preprint arXiv:2411.15594 (2024)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5822"},{"key":"e_1_3_2_1_11_1","volume-title":"Augmenting data with mixup for sentence classification: An empirical study. arXiv preprint arXiv:1905.08941","author":"Guo Hongyu","year":"2019","unstructured":"Hongyu Guo, Yongyi Mao, and Richong Zhang. 2019. Augmenting data with mixup for sentence classification: An empirical study. arXiv preprint arXiv:1905.08941 (2019)."},{"key":"e_1_3_2_1_12_1","volume-title":"Mixco: Mix-up contrastive learning for visual representation. arXiv preprint arXiv:2010.06300","author":"Kim Sungnyun","year":"2020","unstructured":"Sungnyun Kim, Gihun Lee, Sangmin Bae, and Se-Young Yun. 2020. Mixco: Mix-up contrastive learning for visual representation. arXiv preprint arXiv:2010.06300 (2020)."},{"key":"e_1_3_2_1_13_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","unstructured":"Jens Lehmann Robert Isele and et al. 2015. DBpedia \u2013 A large-scale multilingual knowledge base extracted from Wikipedia. Semantic Web (Jan 2015) 167\u2013195. doi:10.3233\/sw-140134","DOI":"10.3233\/sw-140134"},{"key":"e_1_3_2_1_15_1","volume-title":"Sentence embedding leaks more information than you expect: Generative embedding inversion attack to recover the whole sentence. arXiv preprint arXiv:2305.03010","author":"Li Haoran","year":"2023","unstructured":"Haoran Li, Mingshi Xu, and Yangqiu Song. 2023a. Sentence embedding leaks more information than you expect: Generative embedding inversion attack to recover the whole sentence. arXiv preprint arXiv:2305.03010 (2023)."},{"key":"e_1_3_2_1_16_1","volume-title":"Simple-sampling and hard-mixup with prototypes to rebalance contrastive learning for text classification. arXiv preprint arXiv:2405.11524","author":"Li Mengyu","year":"2024","unstructured":"Mengyu Li, Yonghao Liu, Fausto Giunchiglia, Xiaoyue Feng, and Renchu Guan. 2024. Simple-sampling and hard-mixup with prototypes to rebalance contrastive learning for text classification. arXiv preprint arXiv:2405.11524 (2024)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.3115\/1072228.1072378"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.647"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2507157.2507163"},{"key":"e_1_3_2_1_20_1","volume-title":"Language model inversion. arXiv preprint arXiv:2311.13647","author":"Morris John X","year":"2023","unstructured":"John X Morris, Wenting Zhao, Justin T Chiu, Vitaly Shmatikov, and Alexander M Rush. 2023. Language model inversion. arXiv preprint arXiv:2311.13647 (2023)."},{"key":"e_1_3_2_1_21_1","volume-title":"Mixup inference: Better exploiting mixup to defend adversarial attacks. arXiv preprint arXiv:1909.11515","author":"Pang Tianyu","year":"2019","unstructured":"Tianyu Pang, Kun Xu, and Jun Zhu. 2019. Mixup inference: Better exploiting mixup to defend adversarial attacks. arXiv preprint arXiv:1909.11515 (2019)."},{"key":"e_1_3_2_1_22_1","volume-title":"Improving neural machine translation models with monolingual data. arXiv preprint arXiv:1511.06709","author":"Sennrich Rico","year":"2015","unstructured":"Rico Sennrich, Barry Haddow, and Alexandra Birch. 2015. Improving neural machine translation models with monolingual data. arXiv preprint arXiv:1511.06709 (2015)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0197-0"},{"key":"e_1_3_2_1_24_1","volume-title":"Demystifying embedding spaces using large language models. arXiv preprint arXiv:2310.04475","author":"Tennenholtz Guy","year":"2023","unstructured":"Guy Tennenholtz, Yinlam Chow, Chih-Wei Hsu, Jihwan Jeong, Lior Shani, Azamat Tulepbergenov, Deepak Ramachandran, Martin Mladenov, and Craig Boutilier. 2023. Demystifying embedding spaces using large language models. arXiv preprint arXiv:2310.04475 (2023)."},{"key":"e_1_3_2_1_25_1","volume-title":"International conference on machine learning. PMLR, 6438-6447","author":"Verma Vikas","year":"2019","unstructured":"Vikas Verma, Alex Lamb, Christopher Beckham, Amir Najafi, Ioannis Mitliagkas, David Lopez-Paz, and Yoshua Bengio. 2019. Manifold mixup: Better representations by interpolating hidden states. In International conference on machine learning. PMLR, 6438-6447."},{"key":"e_1_3_2_1_26_1","volume-title":"EDA: Easy data augmentation techniques for boosting performance on text classification tasks. arXiv preprint arXiv:1901.11196","author":"Wei Jason","year":"2019","unstructured":"Jason Wei and Kai Zou. 2019. EDA: Easy data augmentation techniques for boosting performance on text classification tasks. arXiv preprint arXiv:1901.11196 (2019)."},{"key":"e_1_3_2_1_27_1","volume-title":"Wilcoxon signed-rank test","author":"Woolson Robert F","year":"2007","unstructured":"Robert F Woolson. 2007. Wilcoxon signed-rank test. Wiley encyclopedia of clinical trials (2007), 1-3."},{"key":"e_1_3_2_1_28_1","volume-title":"Text smoothing: Enhance various data augmentation methods on text classification tasks. arXiv preprint arXiv:2202.13840","author":"Wu Xing","year":"2022","unstructured":"Xing Wu, Chaochen Gao, Meng Lin, Liangjun Zang, Zhongyuan Wang, and Songlin Hu. 2022. Text smoothing: Enhance various data augmentation methods on text classification tasks. arXiv preprint arXiv:2202.13840 (2022)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58526-6_32"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6123"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-5672-8_35"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2433"},{"key":"e_1_3_2_1_33_1","volume-title":"mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412","author":"Zhang Hongyi","year":"2017","unstructured":"Hongyi Zhang, Moustapha Cisse, Yann N Dauphin, and David Lopez-Paz. 2017. mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412 (2017)."},{"key":"e_1_3_2_1_34_1","volume-title":"Map2Text: New Content Generation from Low-Dimensional Visualizations. arXiv e-prints","author":"Zhang Xingjian","year":"2024","unstructured":"Xingjian Zhang, Ziyang Xiong, Shixuan Liu, Yutong Xie, Tolga Ergen, Dongsub Shim, Hua Xu, Honglak Lee, and Qiaozhu Mei. 2024. Map2Text: New Content Generation from Low-Dimensional Visualizations. arXiv e-prints (2024), arXiv-2412."},{"key":"e_1_3_2_1_35_1","volume-title":"Character-level convolutional networks for text classification. Advances in neural information processing systems","author":"Zhang Xiang","year":"2015","unstructured":"Xiang Zhang, Junbo Zhao, and Yann LeCun. 2015. Character-level convolutional networks for text classification. Advances in neural information processing systems, Vol. 28 (2015)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3673791.3698414"}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:31:49Z","timestamp":1786066309000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3817781"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":36,"alternative-id":["10.1145\/3770855.3817781","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3817781","relation":{},"subject":[],"published":{"date-parts":[[2026,8,8]]},"assertion":[{"value":"2026-08-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}