{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T15:05:02Z","timestamp":1784819102530,"version":"3.55.0"},"reference-count":57,"publisher":"Association for Computing Machinery (ACM)","issue":"5","license":[{"start":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T00:00:00Z","timestamp":1784764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62472125"],"award-info":[{"award-number":["62472125"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100021171","name":"Guangdong Basic and Applied Basic Research Foundation","doi-asserted-by":"crossref","award":["2025A1515011258"],"award-info":[{"award-number":["2025A1515011258"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Key Technologies R&D Program of Guangdong Province","award":["2026B0909060001"],"award-info":[{"award-number":["2026B0909060001"]}]},{"name":"Shenzhen Science and Technology Programs","award":["GXWD20231128102922001"],"award-info":[{"award-number":["GXWD20231128102922001"]}]},{"name":"Shenzhen Science and Technology Programs","award":["ZDCY20250901111705007"],"award-info":[{"award-number":["ZDCY20250901111705007"]}]},{"name":"Shenzhen Science and Technology Programs","award":["ZDSYS20230626091203008"],"award-info":[{"award-number":["ZDSYS20230626091203008"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Intell. Syst. Technol."],"published-print":{"date-parts":[[2026,10,31]]},"abstract":"<jats:p>\n                    Instruction tuning has been identified as a crucial technique for optimizing large language models (LLMs) to generate human-aligned responses. Nonetheless, gathering diversified and superior-quality instruction data for such tuning presents notable obstacles, especially in privacy-sensitive domains. Federated instruction tuning (\n                    <jats:monospace>FedIT<\/jats:monospace>\n                    ) has emerged as a promising solution by consolidating collaborative training across multiple data owners, resulting in a privacy-enhancing learning model. Existing\n                    <jats:monospace>FedIT<\/jats:monospace>\n                    studies assume that clients have sufficient training data, however, in reality, many clients only have few-shot samples, leading to either overfitting in federated LLM or degraded performance. At the same time, this federated few-shot environment also increases the risk of training data extraction attacks, as the LLM may well memorize the limited training data. To address these issues, this article proposes a\n                    <jats:italic toggle=\"yes\">novel<\/jats:italic>\n                    federated algorithm,\n                    <jats:monospace>PPFedIT<\/jats:monospace>\n                    , designed to enhance privacy protection and model performance of federated few-shot learning.\n                    <jats:monospace>PPFedIT<\/jats:monospace>\n                    comprises three vital steps on the client side: (1) synthetic data generation, which utilizes the strong generation capacity of LLMs to generate synthetic data, aiming to diversify and enrich local data; (2) parameter isolation training, which respectively updates the parameters of a shared global LLM on the synthetic data and the parameters of local LLMs on the local data, consequently mitigating the noise impact of the synthetic data; (3) local aggregation then sharing mechanism, which mixes the parameters of the global LLM and those of a local LLM first, before uploading them to a server for aggregation. This effectively mitigates data extraction attacks. Extensive experiments on three open source datasets demonstrate\n                    <jats:monospace>PPFedIT<\/jats:monospace>\n                    significantly enhances model performance (averaging 8.4%) and reduces the risk of data extraction attacks (approximately 20%) in practical and challenging federated few-shot scenarios.\n                  <\/jats:p>","DOI":"10.1145\/3806196","type":"journal-article","created":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T14:24:06Z","timestamp":1779805446000},"page":"1-23","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["<tt>PPFedIT<\/tt>\n                    : Towards Privacy-preserving Federated Instruction Tuning with Few-shot Local Examples"],"prefix":"10.1145","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1835-5411","authenticated-orcid":false,"given":"Zhuo","family":"Zhang","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, China and Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6644-4673","authenticated-orcid":false,"given":"Jingyuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5693-1344","authenticated-orcid":false,"given":"Jintao","family":"Huang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0499-727X","authenticated-orcid":false,"given":"Hui","family":"Wang","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9865-2212","authenticated-orcid":false,"given":"Yue","family":"Yu","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9688-7691","authenticated-orcid":false,"given":"Hongzhi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4930-6572","authenticated-orcid":false,"given":"Xun","family":"Zhou","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7764-431X","authenticated-orcid":false,"given":"Lizhen","family":"Qu","sequence":"additional","affiliation":[{"name":"Monash University, Melbourne, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5550-6461","authenticated-orcid":false,"given":"Zenglin","family":"Xu","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,23]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"key":"e_1_3_2_3_2","first-page":"1","volume-title":"Proceedings of the European Symposium on Algorithms","author":"Abboud Amir","year":"2014","unstructured":"Amir Abboud, Kevin Lewi, and Ryan Williams. 2014. Losing weight by gaining edges. In Proceedings of the European Symposium on Algorithms. Springer, 1\u201312."},{"key":"e_1_3_2_4_2","unstructured":"Iz Beltagy Matthew E. Peters and Arman Cohan. 2020. LongFormer: The long-document transformer. arXiv:2004.05150. Retrieved from https:\/\/arxiv.org\/abs\/2004.05150"},{"key":"e_1_3_2_5_2","unstructured":"Vadim Borisov Kathrin Se\u00dfler Tobias Leemann Martin Pawelczyk and Gjergji Kasneci. 2022. Language models are realistic tabular data generators. arXiv:2210.06280. Retrieved from https:\/\/arxiv.org\/abs\/2210.06280"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3534642"},{"key":"e_1_3_2_7_2","first-page":"1877","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D. Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. 2020. Language models are few-shot learners. In Advances in Neural Information Processing Systems, Vol. 33, 1877\u20131901."},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3570361.3613277"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3578356.3592575"},{"key":"e_1_3_2_10_2","first-page":"2633","volume-title":"Proceedings of the 30th USENIX Security Symposium (USENIX Security \u201921)","author":"Carlini Nicholas","year":"2021","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 Proceedings of the 30th USENIX Security Symposium (USENIX Security \u201921), 2633\u20132650."},{"key":"e_1_3_2_11_2","unstructured":"Weilong Dong Xinwei Wu Junzhuo Li Shuangzhi Wu Chao Bian and Deyi Xiong. 2022. FewFedWeight: Few-shot federated learning framework across multiple NLP tasks. arXiv:2212.08354. Retrieved from https:\/\/arxiv.org\/abs\/2212.08354"},{"key":"e_1_3_2_12_2","unstructured":"Qianlong Du Chengqing Zong and Jiajun Zhang. 2023. MoDS: Model-oriented data selection for instruction tuning. arXiv:2311.15653. Retrieved from https:\/\/arxiv.org\/abs\/2311.15653"},{"key":"e_1_3_2_13_2","doi-asserted-by":"crossref","unstructured":"Yann Dubois Xuechen Li Rohan Taori Tianyi Zhang Ishaan Gulrajani Jimmy Ba Carlos Guestrin Percy Liang and Tatsunori B. Hashimoto. 2023. AlpacaFarm: A simulation framework for methods that learn from human feedback. arXiv:2305.14387. Retrieved from https:\/\/arxiv.org\/abs\/2305.14387","DOI":"10.52202\/075280-1308"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1561\/0400000042"},{"key":"e_1_3_2_15_2","unstructured":"Tao Fan Yan Kang Guoqiang Ma Weijing Chen Wenbin Wei Lixin Fan and Qiang Yang. 2023. Fate-LLM: A industrial grade federated learning framework for large language models. arXiv:2310.10049. Retrieved from https:\/\/arxiv.org\/abs\/2310.10049"},{"key":"e_1_3_2_16_2","unstructured":"Liam Fowl Jonas Geiping Steven Reich Yuxin Wen Wojtek Czaja Micah Goldblum and Tom Goldstein. 2022. Decepticons: Corrupted transformers breach privacy in federated learning for language models. arXiv:2201.12675. Retrieved from https:\/\/arxiv.org\/abs\/2201.12675"},{"key":"e_1_3_2_17_2","unstructured":"Leo Gao Jonathan Tow Stella Biderman Sid Black Anthony DiPofi Charles Foster Laurence Golding Jeffrey Hsu Kyle McDonell Niklas Muennighoff et al. 2021. A Framework for Few-Shot Language Model Evaluation. Version v0.0.1. Retrieved from https:\/\/zenodo.org\/records\/5371629"},{"key":"e_1_3_2_18_2","unstructured":"Tianyu Han Lisa C. Adams Jens-Michalis Papaioannou Paul Grundmann Tom Oberhauser Alexander L\u00f6ser Daniel Truhn and Keno K. Bressem. 2023. MedAlpaca\u2014An open-source collection of medical conversational AI models and training data. arXiv:2304.08247. Retrieved from https:\/\/arxiv.org\/abs\/2304.08247"},{"key":"e_1_3_2_19_2","unstructured":"Or Honovich Thomas Scialom Omer Levy and Timo Schick. 2022. Unnatural instructions: Tuning language models with (almost) no human labor. arXiv:2212.09689. Retrieved from https:\/\/arxiv.org\/abs\/2212.09689"},{"key":"e_1_3_2_20_2","unstructured":"Tzu-Ming Harry Hsu Hang Qi and Matthew Brown. 2019. Measuring the effects of non-identical data distribution for federated visual classification. arXiv:1909.06335. Retrieved from https:\/\/arxiv.org\/abs\/1909.06335"},{"key":"e_1_3_2_21_2","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. Retrieved from https:\/\/arxiv.org\/abs\/2106.09685"},{"key":"e_1_3_2_22_2","doi-asserted-by":"crossref","first-page":"304","DOI":"10.1109\/MNET.2024.3353377","article-title":"Federated learning-empowered AI-generated content in wireless networks","volume":"38","author":"Huang Xumin","year":"2024","unstructured":"Xumin Huang, Peichun Li, Hongyang Du, Jiawen Kang, Dusit Niyato, Dong In Kim, and Yuan Wu. 2024. Federated learning-empowered AI-generated content in wireless networks. IEEE Network 38 (2024), 304\u2013313.","journal-title":"IEEE Network"},{"key":"e_1_3_2_23_2","doi-asserted-by":"crossref","unstructured":"Yangsibo Huang Zhao Song Danqi Chen Kai Li and Sanjeev Arora. 2020. TextHide: Tackling data privacy in language understanding tasks. arXiv:2010.06053. Retrieved from https:\/\/arxiv.org\/abs\/2010.06053","DOI":"10.18653\/v1\/2020.findings-emnlp.123"},{"key":"e_1_3_2_24_2","doi-asserted-by":"crossref","unstructured":"Di Jin Eileen Pan Nassim Oufattole Wei-Hung Weng Hanyi Fang and Peter Szolovits. 2020. What disease does this patient have? A large-scale open domain question answering dataset from medical exams. arXiv:2009.13081. Retrieved from https:\/\/arxiv.org\/abs\/2009.13081","DOI":"10.20944\/preprints202105.0498.v1"},{"key":"e_1_3_2_25_2","first-page":"5132","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Karimireddy Sai Praneeth","year":"2020","unstructured":"Sai Praneeth Karimireddy, Satyen Kale, Mehryar Mohri, Sashank Reddi, Sebastian Stich, and Ananda Theertha Suresh. 2020. Scaffold: Stochastic controlled averaging for federated learning. In Proceedings of the International Conference on Machine Learning. PMLR, 5132\u20135143."},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1137\/090756090"},{"key":"e_1_3_2_27_2","unstructured":"Jakub Kone\u010dn\u1ef3 H. Brendan McMahan Felix X. Yu Peter Richt\u00e1rik Ananda Theertha Suresh and Dave Bacon. 2016. Federated learning: Strategies for improving communication efficiency. arXiv:1610.05492. Retrieved from https:\/\/arxiv.org\/abs\/1610.05492"},{"key":"e_1_3_2_28_2","unstructured":"Weirui Kuang Bingchen Qian Zitao Li Daoyuan Chen Dawei Gao Xuchen Pan Yuexiang Xie Yaliang Li Bolin Ding and Jingren Zhou. 2023. FederatedScope-LLM: A comprehensive package for fine-tuning large language models in federated learning. arXiv:2309.00363. Retrieved from https:\/\/arxiv.org\/abs\/2309.00363"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"e_1_3_2_30_2","unstructured":"Ming Li Yong Zhang Zhitao Li Jiuhai Chen Lichang Chen Ning Cheng Jianzong Wang Tianyi Zhou and Jing Xiao. 2023. From quantity to quality: Boosting LLM performance with self-guided data selection for instruction tuning. arXiv:2308.12032. Retrieved from https:\/\/arxiv.org\/abs\/2308.12032"},{"key":"e_1_3_2_31_2","first-page":"429","volume-title":"Proceedings of Machine Learning and Systems","author":"Li Tian","year":"2020","unstructured":"Tian Li, Anit Kumar Sahu, Manzil Zaheer, Maziar Sanjabi, Ameet Talwalkar, and Virginia Smith. 2020. Federated optimization in heterogeneous networks. In Proceedings of Machine Learning and Systems, 429\u2013450."},{"key":"e_1_3_2_32_2","unstructured":"Xian Li Ping Yu Chunting Zhou Timo Schick Luke Zettlemoyer Omer Levy Jason Weston and Mike Lewis. 2023. Self-alignment with instruction backtranslation. arXiv:2308.06259. Retrieved from https:\/\/arxiv.org\/abs\/2308.06259"},{"key":"e_1_3_2_33_2","unstructured":"Xuechen Li Tianyi Zhang Yann Dubois Rohan Taori Ishaan Gulrajani Carlos Guestrin Percy Liang and Tatsunori B. Hashimoto. 2023. AlpacaEval: An Automatic Evaluator of Instruction-Following Models. Retrieved from https:\/\/github.com\/tatsu-lab\/alpaca_eval"},{"key":"e_1_3_2_34_2","unstructured":"Yunshui Li Binyuan Hui Xiaobo Xia Jiaxi Yang Min Yang Lei Zhang Shuzheng Si Junhao Liu Tongliang Liu Fei Huang et al. 2023. One shot learning as instruction data prospector for large language models. arXiv:2312.10302. Retrieved from https:\/\/arxiv.org\/abs\/2312.10302"},{"key":"e_1_3_2_35_2","unstructured":"Bill Yuchen Lin Chaoyang He Zihang Zeng Hulin Wang Yufen Huang Christophe Dupuy Rahul Gupta Mahdi Soltanolkotabi Xiang Ren and Salman Avestimehr. 2021. FedNLP: Benchmarking federated learning methods for natural language processing tasks. arXiv:2104.08815. Retrieved from https:\/\/arxiv.org\/abs\/2104.08815"},{"key":"e_1_3_2_36_2","first-page":"74","volume-title":"Proceedings of the Text Summarization Branches Out","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. Rouge: A package for automatic evaluation of summaries. In Proceedings of the Text Summarization Branches Out, 74\u201381."},{"key":"e_1_3_2_37_2","first-page":"1273","volume-title":"Proceedings of the Artificial Intelligence and Statistics","author":"McMahan Brendan","year":"2017","unstructured":"Brendan McMahan, Eider Moore, Daniel Ramage, Seth Hampson, and Blaise Aguera y Arcas. 2017. Communication-efficient learning of deep networks from decentralized data. In Proceedings of the Artificial Intelligence and Statistics. PMLR, 1273\u20131282."},{"key":"e_1_3_2_38_2","unstructured":"Milad Nasr Nicholas Carlini Jonathan Hayase Matthew Jagielski A. Feder Cooper Daphne Ippolito Christopher A. Choquette-Choo Eric Wallace Florian Tram\u00e8r and Katherine Lee. 2023. Scalable extraction of training data from (production) language models. arXiv:2311.17035. Retrieved from https:\/\/arxiv.org\/abs\/2311.17035"},{"key":"e_1_3_2_39_2","unstructured":"R OpenAI. 2023. Gpt-4 technical report (View in Article 2). arXiv:230308774. Retrieved from https:\/\/arxiv.org\/abs\/2303808774"},{"key":"e_1_3_2_40_2","unstructured":"Baolin Peng Chunyuan Li Pengcheng He Michel Galley and Jianfeng Gao. 2023. Instruction tuning with GPT-4. arXiv:2304.03277. Retrieved from https:\/\/arxiv.org\/abs\/2304.03277"},{"key":"e_1_3_2_41_2","unstructured":"Sashank Reddi Zachary Charles Manzil Zaheer Zachary Garrett Keith Rush Jakub Kone\u010dn\u1ef3 Sanjiv Kumar and H. Brendan McMahan. 2020. Adaptive federated optimization. arXiv:2003.00295. Retrieved from https:\/\/arxiv.org\/abs\/2003.00295"},{"key":"e_1_3_2_42_2","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. Retrieved from https:\/\/arxiv.org\/abs\/2312.15603"},{"key":"e_1_3_2_43_2","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:2307.09288. Retrieved from https:\/\/arxiv.org\/abs\/2307.09288"},{"key":"e_1_3_2_44_2","unstructured":"Pablo Villalobos Jaime Sevilla Lennart Heim Tamay Besiroglu Marius Hobbhahn and Anson Ho. 2022. Will we run out of data? An analysis of the limits of scaling datasets in machine learning. arXiv:2211.04325. Retrieved from https:\/\/arxiv.org\/abs\/2211.04325"},{"key":"e_1_3_2_45_2","unstructured":"Peiyi Wang Lei Li Liang Chen Dawei Zhu Binghuai Lin Yunbo Cao Qi Liu Tianyu Liu and Zhifang Sui. 2023. Large language models are not fair evaluators. arXiv:2305.17926. Retrieved from https:\/\/arxiv.org\/abs\/2305.17926"},{"key":"e_1_3_2_46_2","unstructured":"Yizhong Wang Yeganeh Kordi Swaroop Mishra Alisa Liu Noah A. Smith Daniel Khashabi and Hannaneh Hajishirzi. 2022. Self-instruct: Aligning language model with self generated instructions. arXiv:2212.10560. Retrieved from https:\/\/arxiv.org\/abs\/2212.10560"},{"key":"e_1_3_2_47_2","unstructured":"Can Xu Qingfeng Sun Kai Zheng Xiubo Geng Pu Zhao Jiazhan Feng Chongyang Tao and Daxin Jiang. 2023. WizardLM: Empowering large language models to follow complex instructions. arXiv:2304.12244. Retrieved from https:\/\/arxiv.org\/abs\/2304.12244"},{"key":"e_1_3_2_48_2","doi-asserted-by":"crossref","unstructured":"Rui Ye Wenhao Wang Jingyi Chai Dihan Li Zexi Li Yinda Xu Yaxin Du Yanfeng Wang and Siheng Chen. 2024. OpenFedLLM: Training large language models on decentralized private data via federated learning. arXiv:2402.06954. Retrieved from https:\/\/arxiv.org\/abs\/2402.06954","DOI":"10.1145\/3637528.3671582"},{"key":"e_1_3_2_49_2","unstructured":"Rui Ye Xinyu Zhu Jingyi Chai Siheng Chen and Yanfeng Wang. 2023. Federated learning empowered by generative content. arXiv:2312.05807. Retrieved from https:\/\/arxiv.org\/abs\/2312.05807"},{"key":"e_1_3_2_50_2","unstructured":"Asaf Yehudai Boaz Carmeli Yosi Mass Ofir Arviv Nathaniel Mills Assaf Toledo Eyal Shnarch and Leshem Choshen. 2024. Genie: Achieving human parity in content-grounded datasets generation. arXiv:2401.14367. Retrieved from https:\/\/arxiv.org\/abs\/2401.14367"},{"key":"e_1_3_2_51_2","unstructured":"Jianyi Zhang Saeed Vahidian Martin Kuo Chunyuan Li Ruiyi Zhang Guoyin Wang and Yiran Chen. 2023. Towards building the federated GPT: Federated instruction tuning. arXiv:2305.05644. Retrieved from https:\/\/arxiv.org\/abs\/2305.05644"},{"key":"e_1_3_2_52_2","unstructured":"Peiyuan Zhang Guangtao Zeng Tianduo Wang and Wei Lu. 2024. TinyLlama: An open-source small language model. arXiv:2401.02385. Retrieved from https:\/\/arxiv.org\/abs\/2401.02385"},{"key":"e_1_3_2_53_2","unstructured":"Xinlu Zhang Chenxin Tian Xianjun Yang Lichang Chen Zekun Li and Linda Ruth Petzold. 2023. AlpaCare: Instruction-tuned large language models for medical application. arXiv:2310.14558. Retrieved from https:\/\/arxiv.org\/abs\/2310.14558"},{"key":"e_1_3_2_54_2","doi-asserted-by":"crossref","first-page":"3492","DOI":"10.18653\/v1\/2023.acl-long.193","volume-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Vol. 1: Long Papers)","author":"Zhang Zhuo","year":"2023","unstructured":"Zhuo Zhang, Xiangjing Hu, Jingyuan Zhang, Yating Zhang, Hui Wang, Lizhen Qu, and Zenglin Xu. 2023. FedLegal: The first real-world federated learning benchmark for legal NLP. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Vol. 1: Long Papers), 3492\u20133507."},{"key":"e_1_3_2_55_2","doi-asserted-by":"crossref","first-page":"9963","DOI":"10.18653\/v1\/2023.findings-acl.632","volume-title":"Proceedings of the Annual Meeting of the Association of Computational Linguistics 2023","author":"Zhang Zhuo","year":"2023","unstructured":"Zhuo Zhang, Yuanhang Yang, Yong Dai, Qifan Wang, Yue Yu, Lizhen Qu, and Zenglin Xu. 2023. FedPETuning: When federated learning meets the parameter-efficient tuning methods of pre-trained language models. In Proceedings of the Annual Meeting of the Association of Computational Linguistics 2023. Association for Computational Linguistics (ACL), 9963\u20139977."},{"key":"e_1_3_2_56_2","first-page":"1","volume-title":"Proceedings of the ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Zhao Haodong","year":"2023","unstructured":"Haodong Zhao, Wei Du, Fangqi Li, Peixuan Li, and Gongshen Liu. 2023. FedPrompt: Communication-efficient and privacy-preserving prompt tuning in federated learning. In Proceedings of the ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 1\u20135."},{"key":"e_1_3_2_57_2","volume-title":"Proceedings of the ICLR 2024 Workshop on Navigating and Addressing Data Problems for Foundation Models","author":"Zhao Wanru","year":"2024","unstructured":"Wanru Zhao, Yaxin Du, Nicholas Donald Lane, Siheng Chen, and Yanfeng Wang. 2024. Enhancing data quality in federated fine-tuning of large language models. In Proceedings of the ICLR 2024 Workshop on Navigating and Addressing Data Problems for Foundation Models."},{"key":"e_1_3_2_58_2","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","author":"Zheng Lianmin","year":"2024","unstructured":"Lianmin Zheng, Wei Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric Xing, et al. 2024. Judging LLM-as-a-judge with MT-bench and chatbot arena. In Proceedings of the 37th International Conference on Neural Information Processing Systems."}],"container-title":["ACM Transactions on Intelligent Systems and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3806196","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T14:34:23Z","timestamp":1784817263000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3806196"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,23]]},"references-count":57,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,10,31]]}},"alternative-id":["10.1145\/3806196"],"URL":"https:\/\/doi.org\/10.1145\/3806196","relation":{},"ISSN":["2157-6904","2157-6912"],"issn-type":[{"value":"2157-6904","type":"print"},{"value":"2157-6912","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,23]]},"assertion":[{"value":"2024-10-14","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-28","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-07-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}