{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T15:06:01Z","timestamp":1782313561565,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,3]]},"DOI":"10.1145\/3711896.3737411","type":"proceedings-article","created":{"date-parts":[[2025,8,3]],"date-time":"2025-08-03T20:52:41Z","timestamp":1754254361000},"page":"5470-5481","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["VFLAIR-LLM: A Comprehensive Framework and Benchmark for Split Learning of LLMs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-7559-2834","authenticated-orcid":false,"given":"Zixuan","family":"Gu","sequence":"first","affiliation":[{"name":"School of Software, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4446-5661","authenticated-orcid":false,"given":"Qiufeng","family":"Fan","sequence":"additional","affiliation":[{"name":"Wuxi Innovation Center of Tsinghua AIR, Wuxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6135-8320","authenticated-orcid":false,"given":"Long","family":"Sun","sequence":"additional","affiliation":[{"name":"Wuxi Innovation Center of Tsinghua AIR, Wuxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3800-3533","authenticated-orcid":false,"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"the Hong Kong Polytechnic University, Hong Kong, China and the Shanghai Artificial Intelligence Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9780-4827","authenticated-orcid":false,"given":"Xiaojun","family":"Ye","sequence":"additional","affiliation":[{"name":"School of Software, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,8,3]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1045"},{"key":"e_1_3_2_2_2_1","volume-title":"Code Alpaca: An Instruction-following LLaMA model for code generation. https:\/\/github.com\/sahil280114\/codealpaca.","author":"Chaudhary Sahil","year":"2023","unstructured":"Sahil Chaudhary. 2023. Code Alpaca: An Instruction-following LLaMA model for code generation. https:\/\/github.com\/sahil280114\/codealpaca."},{"key":"e_1_3_2_2_3_1","unstructured":"Guanzhong Chen Zhenghan Qin Mingxin Yang Yajie Zhou Tao Fan Tianyu Du and Zenglin Xu. 2024. Unveiling the Vulnerability of Private Fine-Tuning in Split-Based Frameworks for Large Language Models: A Bidirectionally Enhanced Attack. arxiv:2409.00960 [cs.CR] https:\/\/arxiv.org\/abs\/2409.00960"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.355"},{"key":"e_1_3_2_2_5_1","unstructured":"Karl Cobbe Vineet Kosaraju Mohammad Bavarian Mark Chen Heewoo Jun Lukasz Kaiser Matthias Plappert Jerry Tworek Jacob Hilton Reiichiro Nakano Christopher Hesse and John Schulman. 2021. Training Verifiers to Solve Math Word Problems. arxiv:2110.14168 [cs.LG] https:\/\/arxiv.org\/abs\/2110.14168"},{"key":"e_1_3_2_2_6_1","volume-title":"Free Dolly: Introducing the World's First Truly Open Instruction-Tuned LLM. https:\/\/www.databricks.com\/blog\/2023\/04\/12\/dolly-first-open-commercially-viable-instruction-tuned-llm","author":"Conover Mike","year":"2023","unstructured":"Mike Conover, Matt Hayes, Ankit Mathur, Jianwei Xie, Jun Wan, Sam Shah, Ali Ghodsi, Patrick Wendell, Matei Zaharia, and Reynold Xin. 2023. Free Dolly: Introducing the World's First Truly Open Instruction-Tuned LLM. https:\/\/www.databricks.com\/blog\/2023\/04\/12\/dolly-first-open-commercially-viable-instruction-tuned-llm"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3576915.3616592"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2810103.2813677"},{"key":"e_1_3_2_2_9_1","volume-title":"Label Inference Attacks Against Vertical Federated Learning. In 31st USENIX Security Symposium (USENIX Security 22)","author":"Fu Chong","year":"2022","unstructured":"Chong Fu, Xuhong Zhang, Shouling Ji, Jinyin Chen, Jingzheng Wu, Shanqing Guo, Jun Zhou, Alex X Liu, and Ting Wang. 2022. Label Inference Attacks Against Vertical Federated Learning. In 31st USENIX Security Symposium (USENIX Security 22). USENIX Association, Boston, MA. https:\/\/www.usenix.org\/conference\/usenixsecurity22\/presentation\/fu"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2018.05.003"},{"key":"e_1_3_2_2_11_1","unstructured":"Otkrist Gupta and Ramesh Raskar. 2018b. Distributed learning of deep neural network over multiple agents. arxiv:1810.06060 [cs.LG] https:\/\/arxiv.org\/abs\/1810.06060"},{"key":"e_1_3_2_2_12_1","unstructured":"Dan Hendrycks Collin Burns Saurav Kadavath Akul Arora Steven Basart Eric Tang Dawn Song and Jacob Steinhardt. 2021. Measuring Mathematical Problem Solving With the MATH Dataset. NeurIPS(2021)."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"crossref","unstructured":"Cheng-Yu Hsieh Chun-Liang Li Chih-Kuan Yeh Hootan Nakhost Yasuhisa Fujii Alexander Ratner Ranjay Krishna Chen-Yu Lee and Tomas Pfister. 2023. Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes. arxiv:2305.02301 [cs.CL]","DOI":"10.18653\/v1\/2023.findings-acl.507"},{"key":"e_1_3_2_2_14_1","unstructured":"Edward J. Hu Yelong Shen Phillip Wallis Zeyuan Allen-Zhu Yuanzhi Li Shean Wang Lu Wang and Weizhu Chen. 2021. LoRA: Low-Rank Adaptation of Large Language Models. arxiv:2106.09685 [cs.CL] https:\/\/arxiv.org\/abs\/2106.09685"},{"key":"e_1_3_2_2_15_1","unstructured":"Nam Hyeon-Woo Moon Ye-Bin and Tae-Hyun Oh. 2021. FedPara: Low-Rank Hadamard Product for Communication-Efficient Federated Learning. arxiv:2108.06098 [cs.LG]"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","unstructured":"Kai Kugler Simon M\u00fcnker Johannes H\u00f6hmann and Achim Rettinger. 2024. InvBERT: Reconstructing Text from Contextualized Word Embeddings by inverting the BERT pipeline. (2024). https:\/\/doi.org\/10.48694\/JCLS.3572","DOI":"10.48694\/JCLS.3572"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.881"},{"key":"e_1_3_2_2_18_1","volume-title":"Label Leakage and Protection in Two-party Split Learning. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=cOtBRgsf2fO","author":"Li Oscar","year":"2022","unstructured":"Oscar Li, Jiankai Sun, Xin Yang, Weihao Gao, Hongyi Zhang, Junyuan Xie, Virginia Smith, and Chong Wang. 2022. Label Leakage and Protection in Two-party Split Learning. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=cOtBRgsf2fO"},{"key":"e_1_3_2_2_19_1","unstructured":"Zheng Lin Xuanjie Hu Yuxin Zhang Zhe Chen Zihan Fang Xianhao Chen Ang Li Praneeth Vepakomma and Yue Gao. 2024. SplitLoRA: A Split Parameter-Efficient Fine-Tuning Framework for Large Language Models. arxiv:2407.00952 [cs.LG] https:\/\/arxiv.org\/abs\/2407.00952"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2310.09130"},{"key":"e_1_3_2_2_21_1","volume-title":"PEFT: State-of-the-art Parameter-Efficient Fine-Tuning methods. https:\/\/github.com\/huggingface\/peft.","author":"Mangrulkar Sourab","year":"2022","unstructured":"Sourab Mangrulkar, Sylvain Gugger, Lysandre Debut, Younes Belkada, Sayak Paul, and Benjamin Bossan. 2022. PEFT: State-of-the-art Parameter-Efficient Fine-Tuning methods. https:\/\/github.com\/huggingface\/peft."},{"key":"e_1_3_2_2_22_1","volume-title":"Federated Learning of Deep Networks using Model Averaging. CoRR","author":"McMahan H. Brendan","year":"2016","unstructured":"H. Brendan McMahan, Eider Moore, Daniel Ramage, and Blaise Ag\u00fcera y Arcas. 2016. Federated Learning of Deep Networks using Model Averaging. CoRR, Vol. abs\/1602.05629 (2016). arxiv:1602.05629 http:\/\/arxiv.org\/abs\/1602.05629"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.765"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP40000.2020.00095"},{"key":"e_1_3_2_2_25_1","volume-title":"Raffaella Bernardi, Sandro Pezzelle, Marco Baroni, Gemma Boleda, and Raquel Fern\u00e1ndez.","author":"Paperno Denis","year":"2016","unstructured":"Denis Paperno, Germ\u00e1n Kruszewski, Angeliki Lazaridou, Quan Ngoc Pham, Raffaella Bernardi, Sandro Pezzelle, Marco Baroni, Gemma Boleda, and Raquel Fern\u00e1ndez. 2016. The LAMBADA dataset: Word prediction requiring a broad discourse context. arxiv:1606.06031 [cs.CL]"},{"key":"e_1_3_2_2_26_1","unstructured":"Alec Radford Jeff Wu Rewon Child David Luan Dario Amodei and Ilya Sutskever. 2019. Language Models are Unsupervised Multitask Learners. (2019)."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"crossref","unstructured":"Pranav Rajpurkar Jian Zhang Konstantin Lopyrev and Percy Liang. 2016. SQuAD: 100 000 Questions for Machine Comprehension of Text. arxiv:1606.05250 [cs.CL]","DOI":"10.18653\/v1\/D16-1264"},{"key":"e_1_3_2_2_28_1","unstructured":"Shuo Ren Daya Guo Shuai Lu Long Zhou Shujie Liu Duyu Tang Neel Sundaresan Ming Zhou Ambrosio Blanco and Shuai Ma. 2020. CodeBLEU: a Method for Automatic Evaluation of Code Synthesis. arxiv:2009.10297 [cs.SE] https:\/\/arxiv.org\/abs\/2009.10297"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/jstsp.2015.2442227"},{"key":"e_1_3_2_2_30_1","unstructured":"Xicong Shen Yang Liu Huiqi Liu Jue Hong Bing Duan Zirui Huang Yunlong Mao Ye Wu and Di Wu. 2023. A Split-and-Privatize Framework for Large Language Model Fine-Tuning. arxiv:2312.15603 [cs.CL] https:\/\/arxiv.org\/abs\/2312.15603"},{"key":"e_1_3_2_2_31_1","volume-title":"Meet Shah, Yu Jiang, Xinlei Chen, Devi Parikh, and Marcus Rohrbach. 2019. Towards VQA Models That Can Read. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 8317-8326","author":"Singh Amanpreet","unstructured":"Amanpreet Singh, Vivek Natarjan, Meet Shah, Yu Jiang, Xinlei Chen, Devi Parikh, and Marcus Rohrbach. 2019. Towards VQA Models That Can Read. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 8317-8326."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3372297.3417270"},{"key":"e_1_3_2_2_33_1","volume-title":"Hashimoto","author":"Taori Rohan","year":"2023","unstructured":"Rohan Taori, Ishaan Gulrajani, Tianyi Zhang, Yann Dubois, Xuechen Li, Carlos Guestrin, Percy Liang, and Tatsunori B. Hashimoto. 2023. Stanford Alpaca: An Instruction-following LLaMA model. https:\/\/github.com\/tatsu-lab\/stanford_alpaca."},{"key":"e_1_3_2_2_34_1","unstructured":"Chandra Thapa M. A. P. Chamikara Seyit Camtepe and Lichao Sun. 2022. SplitFed: When Federated Learning Meets Split Learning. arxiv:2004.12088 [cs.LG] https:\/\/arxiv.org\/abs\/2004.12088"},{"key":"e_1_3_2_2_35_1","unstructured":"Meng Tong Kejiang Chen Jie Zhang Yuang Qi Weiming Zhang Nenghai Yu Tianwei Zhang and Zhikun Zhang. 2024. InferDPT: Privacy-Preserving Inference for Black-box Large Language Model. arxiv:2310.12214 [cs.CR] https:\/\/arxiv.org\/abs\/2310.12214"},{"key":"e_1_3_2_2_36_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N. Gomez Lukasz Kaiser and Illia Polosukhin. 2023. Attention Is All You Need. arxiv:1706.03762 [cs.CL]"},{"key":"e_1_3_2_2_37_1","unstructured":"Praneeth Vepakomma Otkrist Gupta Tristan Swedish and Ramesh Raskar. 2018. Split learning for health: Distributed deep learning without sharing raw patient data. arxiv:1812.00564 [cs.LG] https:\/\/arxiv.org\/abs\/1812.00564"},{"key":"e_1_3_2_2_38_1","unstructured":"Pablo Villalobos Anson Ho Jaime Sevilla Tamay Besiroglu Lennart Heim and Marius Hobbhahn. 2024. Will we run out of data? Limits of LLM scaling based on human-generated data. arxiv:2211.04325 [cs.LG] https:\/\/arxiv.org\/abs\/2211.04325"},{"key":"e_1_3_2_2_39_1","volume-title":"Bowman","author":"Wang Alex","year":"2019","unstructured":"Alex Wang, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel R. Bowman. 2019. Glue: A multi-task benchmark and analysis platform for natural language understanding."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i13.17387"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.23919\/CNSM55787.2022.9964646"},{"key":"e_1_3_2_2_42_1","unstructured":"Guangxuan Xiao Ji Lin and Song Han. 2023. Offsite-Tuning: Transfer Learning without Full Model. arxiv:2302.04870 [cs.CL] https:\/\/arxiv.org\/abs\/2302.04870"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3298981"},{"key":"e_1_3_2_2_44_1","unstructured":"Kai Yao Zhaorui Tan Tiandi Ye Lichun Li Yuan Zhao Wenyan Liu Wei Wang and Jianke Zhu. 2024b. ScaleOT: Privacy-utility-scalable Offsite-tuning with Dynamic LayerReplace and Selective Rank Compression. arxiv:2412.09812 [cs.CL] https:\/\/arxiv.org\/abs\/2412.09812"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.hcc.2024.100211"},{"key":"e_1_3_2_2_46_1","unstructured":"Longhui Yu Weisen Jiang Han Shi Jincheng Yu Zhengying Liu Yu Zhang James T Kwok Zhenguo Li Adrian Weller and Weiyang Liu. 2023. MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models. arXiv preprint arXiv:2309.12284(2023)."},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.337"},{"key":"e_1_3_2_2_48_1","unstructured":"Qingru Zhang Minshuo Chen Alexander Bukharin Nikos Karampatziakis Pengcheng He Yu Cheng Weizhu Chen and Tuo Zhao. 2023. AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning. arxiv:2303.10512 [cs.CL]"},{"key":"e_1_3_2_2_49_1","volume-title":"Advances in Neural Information Processing Systems, C. Cortes, N.","author":"Zhang Xiang","year":"2015","unstructured":"Xiang Zhang, Junbo Zhao, and Yann LeCun. 2015. Character-level Convolutional Networks for Text Classification. In Advances in Neural Information Processing Systems, C. Cortes, N. Lawrence, D. Lee, M. Sugiyama, and R. Garnett(Eds.), Vol. 28. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2015\/file\/250cf8b51c773f3f8dc8b4be867a9a02-Paper.pdf"},{"key":"e_1_3_2_2_50_1","volume-title":"SLPerf: a Unified Framework for Benchmarking Split Learning. ArXiv","author":"Zhou Tianchen","year":"2023","unstructured":"Tianchen Zhou, Zhanyi Hu, Bingzhe Wu, and Cen Chen. 2023a. SLPerf: a Unified Framework for Benchmarking Split Learning. ArXiv, Vol. abs\/2304.01502 (2023). https:\/\/api.semanticscholar.org\/CorpusID:257921382"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.337"},{"key":"e_1_3_2_2_52_1","volume-title":"VFLAIR: A Research Library and Benchmark for Vertical Federated Learning. arXiv preprint arXiv:2310.09827(2023).","author":"Zou Tianyuan","year":"2023","unstructured":"Tianyuan Zou, Zixuan Gu, Yu He, Hideaki Takahashi, Yang Liu, Guangnan Ye, and Ya-Qin Zhang. 2023a. VFLAIR: A Research Library and Benchmark for Vertical Federated Learning. arXiv preprint arXiv:2310.09827(2023)."},{"key":"e_1_3_2_2_53_1","volume-title":"Defending Batch-Level Label Inference and Replacement Attacks in Vertical Federated Learning","author":"Zou Tianyuan","year":"2022","unstructured":"Tianyuan Zou, Yang Liu, Yan Kang, Wenhan Liu, Yuanqin He, Zhihao Yi, Qiang Yang, and Ya-Qin Zhang. 2022a. Defending Batch-Level Label Inference and Replacement Attacks in Vertical Federated Learning. IEEE Transactions on Big Data(2022)."},{"key":"e_1_3_2_2_54_1","volume-title":"Defending Batch-Level Label Inference and Replacement Attacks in Vertical Federated Learning","author":"Zou Tianyuan","year":"2022","unstructured":"Tianyuan Zou, Yang Liu, Yan Kang, Wenhan Liu, Yuanqin He, Zhihao Yi, Qiang Yang, and Ya-Qin Zhang. 2022b. Defending Batch-Level Label Inference and Replacement Attacks in Vertical Federated Learning. IEEE Transactions on Big Data(2022)."},{"key":"e_1_3_2_2_55_1","unstructured":"Tianyuan Zou Yang Liu and Ya-Qin Zhang. 2023b. Mutual Information Regularization for Vertical Federated Learning. arXiv preprint arXiv:2301.01142(2023). gr"}],"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\/3711896.3737411","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:58:26Z","timestamp":1777571906000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3711896.3737411"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,3]]},"references-count":55,"alternative-id":["10.1145\/3711896.3737411","10.1145\/3711896"],"URL":"https:\/\/doi.org\/10.1145\/3711896.3737411","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"}}]}}