Federated reasoning LLMs: a survey

Abstract

Reasoning has long been regarded as a distinctive hallmark of human cognition, and recent advances in the artificial intelligence community have increasingly focused on the reasoning large language models (\mathtt{r}\mathtt{L}\mathtt{L}\mathtt{M}\mathtt{s}). However, due to strict privacy regulations, the domain-specific reasoning knowledge is often distributed across multiple data owners, limiting the \mathtt{r}\mathtt{L}\mathtt{L}\mathtt{M}’s ability to fully leverage such valuable resources. In this context, federated learning (FL) has gained increasing attention in both the academia and industry as a promising privacy-preserving paradigm for addressing the challenges in the data-efficient training of \mathtt{r}\mathtt{L}\mathtt{L}\mathtt{M}\mathtt{s}.

In this paper, we conduct a comprehensive survey on federated \mathtt{r}\mathtt{L}\mathtt{L}\mathtt{M}\mathtt{s} and propose a novel taxonomy based on training signals, including training signals derived from raw data, learned representations, and preference feedback. For each category, we emphasize the emerging trends according to how to use FL to enhance reasoning capabilities of \mathtt{r}\mathtt{L}\mathtt{L}\mathtt{M}\mathtt{s} considering the model effectiveness, communication cost and privacy preservation. Finally, we envision future research directions and challenges based on insights from existing studies.

Graphical abstract

Keywords

federated learning / reasoning LLMs / fine tuning / retrieval-augmented generation

References

[1] Proudfoot M, Lacey A R. The Routledge Dictionary of Philosophy. 3rd ed. London: Routledge, 2009

[2] Audi R. The Cambridge Dictionary of Philosophy. Cambridge: Cambridge University Press, 1999

[3] Johnson-Laird P N . Deductive reasoning. Annual Review of Psychology, 1999, 50( 1): 109–135

[4] Xu F, Hao Q, Zong Z, Wang J, Zhang Y, Wang J, Lan X, Gong J, Ouyang T, Meng F, Shao C, Yan Y, Yang Q, Song Y, Ren S, Hu X, Li Y, Feng J, Gao C, Li Y. Towards large reasoning models: a survey of reinforced reasoning with large language models. 2025, arXiv preprint arXiv: 2501.09686

[5] Plaat A, Wong A, Verberne S, Broekens J, van Stein N, Back T. Reasoning with large language models, a survey. 2024, arXiv preprint arXiv: 2407.11511

[6] Bandyopadhyay D, Bhattacharjee S, Ekbal A. Thinking machines: a survey of LLM based reasoning strategies. 2025, arXiv preprint arXiv: 2503.10814

[7] Huang J, Chang K C C. Towards reasoning in large language models: a survey. In: Proceedings of the Findings of the Association for Computational Linguistics: ACL 2023. 2023, 1049−1065

[8] Wei J, Wang X, Schuurmans D, Bosma M, Ichter B, Xia F, Chi E H, Le Q V, Zhou D. Chain-of-thought prompting elicits reasoning in large language models. In: Proceedings of the 36th International Conference on Neural Information Processing Systems. 2022, 1800

[9] Zhang Z, Zhang A, Li M, Smola A. Automatic chain of thought prompting in large language models. In: Proceedings of the 11th International Conference on Learning Representations. 2023

[10] Yao S, Yu D, Zhao J, Shafran I, Griffiths T L, Cao Y, Narasimhan K. Tree of thoughts: deliberate problem solving with large language models. In: Proceedings of the 37th International Conference on Neural Information Processing Systems. 2023, 517

[11] Guo D, Yang D, Zhang H, Song J, Zhang R, , . Deepseek-R1: incentivizing reasoning capability in LLMs via reinforcement learning. 2025, arXiv preprint arXiv: 2501.12948

[12] OpenAI. OpenAI Gpt-4.5 system card. See Openai.com/index/gpt-4–5-system-card/ website, 2025

[13] Anthropic. Claude 3.7 sonnet system card, 2025

[14] Team Q. Qwen3 technical report, 2025

[15] Jung J, Jeong H, Huh E N. Federated learning and RAG integration: a scalable approach for medical large language models. In: Proceedings of 2025 International Conference on Artificial Intelligence in Information and Communication. 2025, 968−973

[16] Kumar J, Chimalakonda S. Code summarization without direct access to code - towards exploring federated LLMs for software engineering. In: Proceedings of the 28th International Conference on Evaluation and Assessment in Software Engineering. 2024, 100−109

[17] Regulation P. General data protection regulation. Intouch, 2018, 25: 1–5

[18] Kairouz P, McMahan H B, Avent B, Bellet A, Bennis M, Bhagoji A N, Bonawitz K, Charles Z, Cormode G, Cummings R, D’Oliveira R G L, Eichner H, Rouayheb S E, Evans D, Gardner J, Garrett Z, Gascón A, Ghazi B, Gibbons P B, Gruteser M, Harchaoui Z, He C, He L, Huo Z, Hutchinson B, Hsu J, Jaggi M, Javidi T, Joshi G, Khodak M, Konecný J, Korolova A, Koushanfar F, Koyejo S, Lepoint T, Liu Y, Mittal P, Mohri M, Nock R, Özgür A, Pagh R, Qi H, Ramage D, Raskar R, Raykova M, Song D, Song W, Stich S U, Sun Z, Suresh A T, Tramèr F, Vepakomma P, Wang J, Xiong L, Xu Z, Yang Q, Yu F X, Yu H, Zhao S . Advances and open problems in federated learning. Foundations and Trends® in Machine Learning, 2021, 14( 1-2): 1–210

[19] Yang Q, Liu Y, Chen T, Tong Y . Federated machine learning: concept and applications. ACM Transactions on Intelligent Systems and Technology (TIST), 2019, 10( 2): 12

[20] Liu F, Zheng Z, Shi Y, Tong Y, Zhang Y . A survey on federated learning: a perspective from multi-party computation. Frontiers of Computer Science, 2024, 18( 1): 181336

[21] Wei S, Zhang Y, Zhou Z, Zhang T, Xu K . FedSM: a practical federated shared mobility system. Proceedings of the VLDB Endowment, 2024, 17( 12): 4445–4448

[22] Song T, Tong Y, Wei S. Profit allocation for federated learning. In: Proceedings of 2019 IEEE International Conference on Big Data. 2019, 2577−2586

[23] Tong Y, Zeng Y, Zhou Z, Liu B, Shi Y, Li S, Xu K, Lv W . Federated computing: query, learning, and beyond. IEEE Data Engineering Bulletin, 2023, 46( 1): 9–26

[24] Zhang J, Yang H F, Li A, Guo X, Wang P, Wang H, Chen Y, Li H. MLLM-FL: multimodal large language model assisted federated learning on heterogeneous and long-tailed data. 2024, arXiv preprint arXiv: 2409.06067

[25] Yang H, Sui M, Liu S, Qian X, Zhang Z, Liu B . Research on key technologies for cross-cloud federated training of large language models. Academic Journal of Computing & Information Science, 2024, 7( 11): 42–49

[26] Sani L, Iacob A, Cao Z, Marino B, Gao Y, Paulik T, Zhao W, Shen W F, Aleksandrov P, Qiu X, Lane N D. The future of large language model pre-training is federated. In: Proceedings of the International Workshop on Federated Foundation Models in Conjunction with NeurIPS. 2024

[27] Shu Y, Hu W, Ng S K, Low B K H, Yu F R. Ferret: federated full-parameter tuning at scale for large language models. In: Proceedings of the International Workshop on Federated Foundation Models in Conjunction with NeurIPS. 2024

[28] Cai Z, Chen H, Zhu G. FeedSign: robust full-parameter federated fine-tuning of large models with extremely low communication overhead of one bit. 2025, arXiv preprint arXiv: 2501.17610

[29] Zhang Z, Cai D, Zhang Y, Xu M, Wang S, Zhou A. FedRDMA: communication-efficient cross-silo federated LLM via chunked RDMA transmission. In: Proceedings of the 4th Workshop on Machine Learning and Systems. 2024, 126−133

[30] Xu M, Cai D, Wu Y, Li X, Wang S. FwdLLM: efficient federated finetuning of large language models with perturbed inferences. In: Proceedings of 2024 USENIX Conference on USENIX Annual Technical Conference. 2024, 579−596

[31] Wang L, Wang Z, Tang X. Save it all: enabling full parameter tuning for federated large language models via cycle black gradient descent. 2024, arXiv preprint arXiv: 2406.11187

[32] Ling Z, Chen D, Yao L, Li Y, Shen Y. On the convergence of zeroth-order federated tuning for large language models. In: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 2024, 1827−1838

[33] Qin Z, Chen D, Qian B, Ding B, Li Y, Deng S. Federated full-parameter tuning of billion-sized language models with communication cost under 18 kilobytes. In: Proceedings of the 41st International Conference on Machine Learning. 2024, 1686

[34] Zhang J, Vahidian S, Kuo M, Li C, Zhang R, Yu T, Wang G, Chen Y. Towards building the federatedgpt: federated instruction tuning. In: Proceedings of 2024 IEEE International Conference on Acoustics, Speech and Signal Processing. 2024, 6915−6919

[35] Du Y, Ye R, Yuchi F, Zhao W, Qu J, Wang Y, Chen S. Data quality control in federated instruction-tuning of large language models. 2024, arXiv preprint arXiv: 2410.11540

[36] Qin Z, Wu Z, He B, Deng S. Federated data-efficient instruction tuning for large language models. 2024, arXiv preprint arXiv: 2410.10926

[37] Ye R, Ge R, Yuchi F, Chai J, Wang Y, Chen S. Leveraging unstructured text data for federated instruction tuning of large language models. In: Proceedings of the Federated Learning in the Age of Foundation Models - FL 2024 International Workshops. 2025, 119−131

[38] Zhang Z, Zhang J, Huang J, Qu L, Zhang H, Wang Q, Zhou X, Xu Z. FewFedPIT: towards privacy-preserving and few-shot federated instruction tuning. 2024, arXiv preprint arXiv: 2403.06131

[39] Liu X, Pang T, Fan C. Federated prompting and chain-of-thought reasoning for improving LLMs answering. In: Proceedings of the 16th International Conference on Knowledge Science, Engineering and Management. 2023, 3−11

[40] Seo J, Zhang N, Rong C. Flexible and secure code deployment in federated learning using large language models: prompt engineering to enhance malicious code detection. In: Proceedings of 2023 IEEE International Conference on Cloud Computing Technology and Science. 2023, 341−349

[41] Wu P, Li K, Nan J, Wang F. Federated in-context LLM agent learning. 2024, arXiv preprint arXiv: 2412.08054

[42] Pan B, Huang W, Shi Y. Federated learning from vision-language foundation models: theoretical analysis and method. In: Proceedings of the 38th International Conference on Neural Information Processing Systems. 2024, 30590−30623

[43] Su S, Yang M, Li B, Xue X. Federated adaptive prompt tuning for multi-domain collaborative learning. In: Proceedings of the 38th AAAI Conference on Artificial Intelligence. 2024, 15117−15125

[44] Che T, Liu J, Zhou Y, Ren J, Zhou J, Sheng V, Dai H, Dou D. Federated learning of large language models with parameter-efficient prompt tuning and adaptive optimization. In: Proceedings of 2023 Conference on Empirical Methods in Natural Language Processing. 2023, 7871−7888

[45] Guo T, Guo S, Wang J, Tang X, Xu W . PromptFL: let federated participants cooperatively learn prompts instead of models - federated learning in age of foundation model. IEEE Transactions on Mobile Computing, 2024, 23( 5): 5179–5194

[46] Wu J, Chen S, Yang Y, Li Y, Hou S, Jing R, Wang Z, Chen W, Tian Z. FedDTPT: federated discrete and transferable prompt tuning for black-box large language models. 2024, arXiv preprint arXiv: 2411.00985

[47] Gong S, Cui C, Zhang C, Wang W, Nie X, Zhu L. Federated domain generalization via prompt learning and aggregation. 2024, arXiv preprint arXiv: 2411.10063

[48] Sun J, Xu Z, Yin H, Yang D, Xu D, Liu Y, Du Z, Chen Y, Roth H R. FedBPT: efficient federated black-box prompt tuning for large language models. In: Proceedings of the 41st International Conference on Machine Learning. 2024

[49] Zhuang W, Chen C, Lyu L. When foundation model meets federated learning: motivations, challenges, and future directions. 2023, arXiv preprint arXiv: 2306.15546

[50] Yao Y, Zhang J, Wu J, Huang C, Xia Y, Yu T, Zhang R, Kim S, Rossi R, Li A, Yao L, McAuley J, Chen Y, Joe-Wong C. Federated large language models: current progress and future directions. 2024, arXiv preprint arXiv: 2409.15723

[51] Ren C, Yu H, Peng H, Tang X, Zhao B, Yi L, Tan A Z, Gao Y, Li A, Li X, Li Z, Yang Q. Advances and open challenges in federated foundation models. IEEE Communications Surveys & Tutorials, 2025

[52] Fan T, Gu H, Cao X, Chan C S, Chen Q, Chen Y, Feng Y, Gu Y, Geng J, Luo B, Liu S, Ong W K, Ren C, Shao J, Sun C, Tang X, Tae H X, Tong Y, Wei S, Wu F, Xi W, Xu M, Yang H, Yang X, Yan J, Yu H, Yu H, Zhang T, Zhang Y, Zhang X, Zheng Z, Fan L, Yang Q. Ten challenging problems in federated foundation models. IEEE Transactions on Knowledge and Data Engineering, 2025

[53] Woisetschläger H, Erben A, Wang S, Mayer R, Jacobsen H A. A survey on efficient federated learning methods for foundation model training. In: Proceedings of the 33rd International Joint Conference on Artificial Intelligence. 2024, 8317−8325

[54] Hu J, Wang D, Wang Z, Pang X, Xu H, Ren J, Ren K. Federated large language model: solutions, challenges and future directions. IEEE Wireless Communications, 2024

[55] Li S, Ye F, Fang M, Zhao J, Chan Y H, Ngai E C H, Voigt T. Synergizing foundation models and federated learning: a survey. 2024, arXiv preprint arXiv: 2406.12844

[56] Wang Z, Shen Z, He Y, Sun G, Wang H, Lyu L, Li A. FLoRA: federated fine-tuning large language models with heterogeneous low-rank adaptations. In: Proceedings of the 38th International Conference on Neural Information Processing Systems. 2024, 22513−22533

[57] Kumar J, Chimalakonda S. Code review automation via multi-task federated LLM — an empirical study. 2024, arXiv preprint arXiv: 2412.15676

[58] Singhal R, Ponkshe K, Vartak R, Varshney L R, Vepakomma P. Fed-SB: a silver bullet for extreme communication efficiency and performance in (private) federated LoRA fine-tuning. 2025, arXiv preprint arXiv: 2502.15436

[59] Tastan N, Nandakumar K. A framework for double-blind federated adaptation of foundation models. 2025, arXiv preprint arXiv: 2502.01289

[60] Saha P, Mishra D, Wagner F, Kamnitsas K, Noble J A. FedPIA−permuting and integrating adapters leveraging Wasserstein barycenters for finetuning foundation models in multi-modal federated learning. In: Proceedings of the 39th AAAI Conference on Artificial Intelligence. 2025, 20228−20236

[61] Sun Y, Li Z, Li Y, Ding B. Improving LoRA in privacy-preserving federated learning. In: Proceedings of the 12th International Conference on Learning Representations. 2024

[62] Yang Y, Long G, Shen T, Jiang J, Blumenstein M. Dual-personalizing adapter for federated foundation models. In: Proceedings of the 38th International Conference on Neural Information Processing Systems. 2024, 39409−39433

[63] Liu J, Ren J, Jin R, Zhang Z, Zhou Y, Valduriez P, Dou D. Fisher information-based efficient curriculum federated learning with large language models. In: Proceedings of 2024 Conference on Empirical Methods in Natural Language Processing. 2024, 10497−10523

[64] Zhao Q, Qu C, Chen C, Fan M, Wang Y. FedMCP: parameter-efficient federated learning with model-contrastive personalization. In: Proceedings of 2024 IEEE 30th International Conference on Parallel and Distributed Systems. 2024, 246−253

[65] Wu P, Li K, Wang T, Dong Y, Leung V C M, Wang F . FedFMSL: federated learning of foundation models with sparsely activated LoRA. IEEE Transactions on Mobile Computing, 2024, 23( 12): 15167–15181

[66] Dong C, Xie Y, Ding B, Shen Y, Li Y. Tunable soft prompts are messengers in federated learning. In: Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2023. 2023, 14665−14675

[67] Fan T, Ma G, Kang Y, Gu H, Song Y, Fan L, Chen K, Yang Q. FedMKT: federated mutual knowledge transfer for large and small language models. In: Proceedings of the 31st International Conference on Computational Linguistics. 2025, 243−255

[68] Fan T, Kang Y, Ma G, Fan L, Chen K, Yang Q. FedCoLLM: a parameter-efficient federated co-tuning framework for large and small language models. 2024, arXiv preprint arXiv: 2411.11707

[69] Wu F, Li Z, Li Y, Ding B, Gao J. FedBiOT: LLM local fine-tuning in federated learning without full model. In: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 2024, 3345−3355

[70] Fan T, Ma G, Song Y, Fan L, Chen K, Yang Q. PPC-GPT: federated task-specific compression of large language models via pruning and chain-of-thought distillation. 2025, arXiv preprint arXiv: 2502.15857

[71] Ma X, Liu J, Wang J, Zhang X. FedID: federated interactive distillation for large-scale pretraining language models. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023, 8566−8577

[72] Chen H, Zhang Y, Krompass D, Gu J, Tresp V. FedDAT: an approach for foundation model finetuning in multi-modal heterogeneous federated learning. In: Proceedings of the 38th AAAI Conference on Artificial Intelligence. 2024, 11285−11293

[73] Peng Z, Fan X, Chen Y, Wang Z, Pan S, Wen C, Zhang R, Wang C. FedPFT: federated proxy fine-tuning of foundation models. In: Proceedings of the 33rd International Joint Conference on Artificial Intelligence. 2024, 4806−4814

[74] Gao Z, Zhang Y, Zhang Z, Gong Y, Guo Y. FedPT: federated proxy-tuning of large language models on resource-constrained edge devices. 2024, arXiv preprint arXiv: 2410.00362

[75] Wu X, Lin W Y, Willmott D, Condessa F, Huang Y, Li Z, Ganesh M R. Leveraging foundation models to improve lightweight clients in federated learning. 2023, arXiv preprint arXiv: 2311.08479

[76] Qi J, Zhou Q, Lei L, Zheng K. Federated reinforcement learning: techniques, applications, and open challenges. 2021, arXiv preprint arXiv: 2108.11887

[77] Srewa M, Zhao T, Elmalaki S. PluralLLM: pluralistic alignment in LLMS via federated learning. In: Proceedings of the 3rd International Workshop on Human-Centered Sensing, Modeling, and Intelligent Systems. 2025, 64−69

[78] Wu F, Liu X, Wang H, Wang X, Su L, Gao J. Towards federated RLHF with aggregated client preference for LLMs. In: Proceedings of the 13th International Conference on Learning Representations. 2025

[79] Fan F X, Tan C, Ong Y S, Wattenhofer R, Ooi W T. FedRLHF: a convergence-guaranteed federated framework for privacy-preserving and personalized RLHF. 2024, arXiv preprint arXiv: 2412.15538

[80] Spadea F, Seneviratne O. Federated fine-tuning of large language models: Kahneman-Tversky vs. direct preference optimization. 2025, arXiv preprint arXiv: 2502.14187

[81] Zhao W X, Zhou K, Li J, Tang T, Wang X, Hou Y, Min Y, Zhang B, Zhang J, Dong Z, Du Y, Yang C, Chen Y, Chen Z, Jiang J, Ren R, Li Y, Tang X, Liu Z, Liu P, Nie J Y, Wen J R. A survey of large language models. 2023, arXiv preprint arXiv: 2303.18223

[82] El-Kassas W S, Salama C R, Rafea A A, Mohamed H K . Automatic text summarization: a comprehensive survey. Expert Systems with Applications, 2021, 165: 113679

[83] NLLB Team . Scaling neural machine translation to 200 languages. Nature, 2024, 630( 8018): 841–846

[84] Su Y, Lan T, Wang Y, Yogatama D, Kong L, Collier N. A contrastive framework for neural text generation. In: Proceedings of the 36th International Conference on Neural Information Processing Systems. 2022, 1566

[85] Achiam J, Adler S, Agarwal S, Ahmad L, Akkaya I, , . GPT-4 technical report. 2023, arXiv preprint arXiv: 2303.08774

[86] Anil R, Dai A M, Firat O, Johnson M, Lepikhin D, , . PaLM 2 technical report. 2023, arXiv preprint arXiv: 2305.10403

[87] Touvron H, Martin L, Stone K, Albert P, Almahairi A, , . Llama 2: open foundation and fine-tuned chat models. 2023, arXiv preprint arXiv: 2307.09288

[88] Wei J, Tay Y, Bommasani R, Raffel C, Zoph B, Borgeaud S, Yogatama D, Bosma M, Zhou D, Metzler D, Chi E H, Hashimoto T, Vinyals O, Liang P, Dean J, Fedus W. Emergent abilities of large language models. Transactions on Machine Learning Research, 2022, 2022

[89] Kojima T, Gu S S, Reid M, Matsuo Y, Iwasawa Y. Large language models are zero-shot reasoners. In: Proceedings of the 36th International Conference on Neural Information Processing Systems. 2022, 1613

[90] Yu F, Zhang H, Tiwari P, Wang B . Natural language reasoning, a survey. ACM Computing Surveys, 2024, 56( 12): 304

[91] Zhu D, Wei X, Zhao G, Wu W, Zou H, Ran J, Wang X, Sun L, Zhang X, Li S. Chain-of-thought matters: improving long-context language models with reasoning path supervision. 2025, arXiv preprint arXiv: 2502.20790

[92] Zhang X, Wang D, Dou L, Zhu Q, Che W . A survey of table reasoning with large language models. Frontiers of Computer Science, 2025, 19( 9): 199348

[93] Yang A, Zhang B, Hui B, Gao B, Yu B, Li C, Liu D, Tu J, Zhou J, Lin J, Lu K, Xue M, Lin R, Liu T, Ren X, Zhang Z. Qwen2.5-math technical report: toward mathematical expert model via self-improvement. 2024, arXiv preprint arXiv: 2409.12122

[94] Grattafiori A, Dubey A, Jauhri A, Pandey A, Kadian A, , . The llama 3 herd of models. 2024, arXiv preprint arXiv: 2407.21783

[95] Guo Z, Zhang R, Tong C, Zhao Z, Gao P, Li H, Heng P A. Can we generate images with CoT? Let’s verify and reinforce image generation step by step. 2025, arXiv preprint arXiv: 2501.13926

[96] Besta M, Blach N, Kubicek A, Gerstenberger R, Podstawski M, Gianinazzi L, Gajda J, Lehmann T, Niewiadomski H, Nyczyk P, Hoefler T. Graph of thoughts: solving elaborate problems with large language models. In: Proceedings of the 38th AAAI Conference on Artificial Intelligence. 2024, 17682−17690

[97] Cobbe K, Kosaraju V, Bavarian M, Chen M, Jun H, Kaiser L, Plappert M, Tworek J, Hilton J, Nakano R, Hesse C, Schulman J. Training verifiers to solve math word problems. 2021, arXiv preprint arXiv: 2110.14168

[98] Wang J, Wang X, Lyu L, Chen J, Ma F. FEDMEKI: a benchmark for scaling medical foundation models via federated knowledge injection. In: Proceedings of the 38th International Conference on Neural Information Processing Systems. 2024

[99] Li X, Peng L, Wang Y P, Zhang W . Open challenges and opportunities in federated foundation models towards biomedical healthcare. BioData Mining, 2025, 18( 1): 2

[100] Liu C, Luo Y, Xu Y, Du B . Foundation models matter: federated learning for multi-center tuberculosis diagnosis via adaptive regularization and model-contrastive learning. World Wide Web, 2024, 27( 3): 30

[101] Kumar J, Janapati V L S, Tanguturi M R, Chimalakonda S. I can’t share code, but I need translation -- an empirical study on code translation through federated LLM. 2025, arXiv preprint arXiv: 2501.05724

[102] Anonymous Hackers. Is the deep web 90% of the internet? See Anonymoushackers.net/dark-web-news/is-the-deep-web-90-of-the-internet/ website, 2025

[103] de la Torre L. A guide to the California consumer privacy act of 2018. See Papers.ssrn.com/sol3/papers.cfm?abstract_id=3275571 website, 2018

[104] Baracaldo N. Is federated learning still alive in the foundation model era? In: Proceedings of the AAAI 2024 Spring Symposium Series. 2024, 293

[105] Bonawitz K, Ivanov V, Kreuter B, Marcedone A, McMahan H B, Patel S, Ramage D, Segal A, Seth K. Practical secure aggregation for privacy-preserving machine learning. In: Proceedings of 2017 ACM SIGSAC Conference on Computer and Communications Security. 2017, 1175−1191

[106] Chua T J, Yu W, Zhao J, Lam K Y. FedPEAT: convergence of federated learning, parameter-efficient fine tuning, and emulator assisted tuning for artificial intelligence foundation models with mobile edge computing. 2023, arXiv preprint arXiv: 2310.17491

[107] Dwork C. Differential privacy. In: Proceedings of the 33rd International Colloquium on Automata, Languages and Programming. 2006, 1−12

[108] Dwork C. Differential privacy: a survey of results. In: Proceedings of the 5th International Conference on Theory and Applications of Models of Computation. 2008, 1−19

[109] Gentry C. Fully homomorphic encryption using ideal lattices. In: Proceedings of the 41st annual ACM Symposium on Theory of Computing. 2009, 169−178

[110] Zhao C, Zhao S, Zhao M, Chen Z, Gao C Z, Li H, Tan Y A . Secure multi-party computation: theory, practice and applications. Information Sciences, 2019, 476: 357–372

[111] Yao A C. Protocols for secure computations. In: Proceedings of the 23rd Annual Symposium on Foundations of Computer Science. 1982, 160−164

[112] Kifer D, Machanavajjhala A. No free lunch in data privacy. In: Proceedings of the 2011 ACM SIGMOD International Conference on Management of Data. 2011, 193−204

[113] Yang L, Chen W, He X, Wei S, Xu Y, Zhou Z, Tong Y. FedGTP: exploiting inter-client spatial dependency in federated graph-based traffic prediction. In: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 2024, 6105−6116

[114] Sun B, Zhang H, Wu Z, Zhang Y, Li T . Adaptive spatiotemporal graph convolutional networks for motor imagery classification. IEEE Signal Processing Letters, 2021, 28: 219–223

[115] Collobert R, Weston J. A unified architecture for natural language processing: deep neural networks with multitask learning. In: Proceedings of the 25th International Conference on Machine Learning. 2008, 160−167

[116] Xie Q, Dai Z, Hovy E, Luong M T, Le Q V. Unsupervised data augmentation for consistency training. In: Proceedings of the 34th International Conference on Neural Information Processing Systems. 2020, 525

[117] Zhou D, Bousquet O, Lal T N, Weston J, Schölkopf B. Learning with local and global consistency. In: Proceedings of the 17th International Conference on Neural Information Processing Systems. 2003, 321−328

[118] Houlsby N, Giurgiu A, Jastrzebski S, Morrone B, De Laroussilhe Q, Gesmundo A, Attariyan M, Gelly S. Parameter-efficient transfer learning for NLP. In: Proceedings of the 36th International Conference on Machine Learning. 2019, 2790−2799

[119] Sanh V, Debut L, Chaumond J, Wolf T. DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. 2019, arXiv preprint arXiv: 1910.01108

[120] Brown T B, Mann B, Ryder N, Subbiah M, Kaplan J, Dhariwal P, Neelakantan A, Shyam P, Sastry G, Askell A, Agarwal S, Herbert-Voss A, Krueger G, Henighan T, Child R, Ramesh A, Ziegler D M, Wu J, Winter C, Hesse C, Chen M, Sigler E, Litwin M, Gray S, Chess B, Clark J, Berner C, McCandlish S, Radford A, Sutskever I, Amodei D. Language models are few-shot learners. In: Proceedings of the 34th International Conference on Neural Information Processing Systems. 2020, 159

[121] Bonawitz K, Eichner H, Grieskamp W, Huba D, Ingerman A, Ivanov V, Kiddon C, Konečný J, Mazzocchi S, McMahan B, Van Overveldt T, Petrou D, Ramage D, Roselander J. Towards federated learning at scale: system design. In: Proceedings of the 2nd Conference on Machine Learning and Systems. 2019

[122] Guo W, Zhuang F, Zhang X, Tong Y, Dong J . A comprehensive survey of federated transfer learning: challenges, methods and applications. Frontiers of Computer Science, 2024, 18( 6): 186356

[123] Jin H, Peng Y, Yang W, Wang S, Zhang Z. Federated reinforcement learning with environment heterogeneity. In: Proceedings of the 25th International Conference on Artificial Intelligence and Statistics. 2022, 18−37

[124] Robbins H, Monro S . A stochastic approximation method. The Annals of Mathematical Statistics, 1951, 22( 3): 400–407

[125] Kingma D P, Ba J. Adam: a method for stochastic optimization. In: Proceedings of the 3rd International Conference on Learning Representations. 2015

[126] Lee G, Jeong M, Shin Y, Bae S, Yun S Y. Preservation of the global knowledge by not-true distillation in federated learning. In: Proceedings of the 36th International Conference on Neural Information Processing Systems. 2022, 2787

[127] Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez A N, Kaiser Ł, Polosukhin I. Attention is all you need. In: Proceedings of the 31st International Conference on Neural Information Processing Systems. 2017, 6000−6010

[128] Christiano P F, Leike J, Brown T B, Martic M, Legg S, Amodei D. Deep reinforcement learning from human preferences. In: Proceedings of the 31st International Conference on Neural Information Processing Systems. 2017, 4302−4310

[129] Gu J, Jiang X, Shi Z, Tan H, Zhai X, Xu C, Li W, Shen Y, Ma S, Liu H, Wang Y, Guo J. A survey on LLM-as-a-judge. 2024, arXiv preprint arXiv: 2411.15594

[130] Wen B, Zhang X. Enhancing reasoning to adapt large language models for domain-specific applications. 2025, arXiv preprint arXiv: 2502.04384

[131] Ouyang L, Wu J, Jiang X, Almeida D, Wainwright C L, Mishkin P, Zhang C, Agarwal S, Slama K, Ray A, Schulman J, Hilton J, Kelton F, Miller L, Simens M, Askell A, Welinder P, Christiano P, Leike J, Lowe R. Training language models to follow instructions with human feedback. In: Proceedings of the 36th International Conference on Neural Information Processing Systems. 2022, 2011

[132] Zhu L, Liu Z, Han S. Deep leakage from gradients. In: Proceedings of the 33rd International Conference on Neural Information Processing Systems. 2019, 1323

[133] Wang H, Sreenivasan K, Rajput S, Vishwakarma H, Agarwal S, Sohn J Y, Lee K, Papailiopoulos D. Attack of the tails: yes, you really can backdoor federated learning. In: Proceedings of the 34th International Conference on Neural Information Processing Systems. 2020, 1348

[134] Wang F, Hugh E, Li B . More than enough is too much: adaptive defenses against gradient leakage in production federated learning. IEEE/ACM Transactions on Networking, 2024, 32( 4): 3061–3075

[135] Wang Z, Du Y, Ma X, Jiang Y, Qian Z, Chen S. Federated instruction tuning of LLMs with domain coverage augmentation. 2024, arXiv preprint arXiv: 2409.20135

[136] Zhang R, Wang Y, Zhou Z, Ren Z, Tong Y, Xu K. Data source selection in federated learning: a submodular optimization approach. In: Proceedings of the 27th International Conference on Database Systems for Advanced Applications. 2022, 606−614

[137] Fu L, Zhang H, Gao G, Zhang M, Liu X . Client selection in federated learning: principles, challenges, and opportunities. IEEE Internet of Things Journal, 2023, 10( 24): 21811–21819

[138] Wei S, Tong Y, Zhou Z, Song T. Efficient and fair data valuation for horizontal federated learning. In: Yang Q, Fan L, Yu H, eds. Federated Learning: Privacy and Incentive. Cham: Springer, 2020, 139−152

[139] Wei S, Tong Y, Zhou Z, He T, Xu Y. Efficient data valuation approximation in federated learning: A sampling-based approach. In: Proceeding of the 41st IEEE International Conference on Data Engineering. 2025, 2922–2934

[140] West R, Aydin R . The AI alignment paradox. Communications of the ACM, 2025, 68( 3): 24–26

[141] Ye R, Chai J, Liu X, Yang Y, Wang Y, Chen S. Emerging safety attack and defense in federated instruction tuning of large language models. In: Proceedings of the 13th International Conference on Learning Representations. 2025

[142] White J, Fu Q, Hays S, Sandborn M, Olea C, Gilbert H, Elnashar A, Spencer-Smith J, Schmidt D C. A prompt pattern catalog to enhance prompt engineering with ChatGPT. In: Proceedings of the 30th Conference on Pattern Languages of Programs. 2023, 5

[143] Weng P Y, Hoang M, Nguyen L M, Thai M T, Weng T W, Hoang T N. Probabilistic federated prompt-tuning with non-IID and imbalanced data. In: Proceedings of the 38th International Conference on Neural Information Processing Systems. 2024

[144] Church K W . Word2vec. Natural Language Engineering, 2017, 23( 1): 155–162

[145] Lin Z, Sun Y, Shi Y, Wang X, Huang L, Shen L, Tao D. Efficient federated prompt tuning for black-box large pre-trained models. 2023, arXiv preprint arXiv: 2310.03123

[146] Igel C, Hansen N, Roth S . Covariance matrix adaptation for multi-objective optimization. Evolutionary Computation, 2007, 15( 1): 1–28

[147] Zhang C, Long G, Guo H, Fang X, Song Y, Liu Z, Zhou G, Zhang Z, Liu Y, Yang B. Federated adaptation for foundation model-based recommendations. In: Proceedings of the 33rd International Joint Conference on Artificial Intelligence. 2024, 5453−5461

[148] Zhang Z, Yang Y, Dai Y, Wang Q, Yu Y, Qu L, Xu Z. FedPETuning: when federated learning meets the parameter-efficient tuning methods of pre-trained language models. In: Proceedings of the Findings of the Association for Computational Linguistics: ACL 2023. 2023, 9963−9977

[149] Mao Y, Ge Y, Fan Y, Xu W, Mi Y, Hu Z, Gao Y . A survey on LoRA of large language models. Frontiers of Computer Science, 2025, 19( 7): 197605

[150] Gou J, Yu B, Maybank S J, Tao D . Knowledge distillation: a survey. International Journal of Computer Vision, 2021, 129( 6): 1789–1819

[151] Zhang Y, Zeng D, Luo J, Fu X, Chen G, Xu Z, King I . A survey of trustworthy federated learning: issues, solutions, and challenges. ACM Transactions on Intelligent Systems and Technology, 2024, 15( 6): 112

[152] Rafailov R, Sharma A, Mitchell E, Manning C D, Ermon S, Finn C. Direct preference optimization: your language model is secretly a reward model. In: Proceedings of the 37th International Conference on Neural Information Processing Systems. 2023

[153] Pan Y, Su Z, Wang Y, Guo S, Liu H, Li R, Wu Y. Cloud-edge collaborative large model services: challenges and solutions. IEEE Network, 2024

[154] Chen Q, Qin L, Liu J, Peng D, Guan J, Wang P, Hu M, Zhou Y, Gao T, Che W. Towards reasoning era: a survey of long chain-of-thought for reasoning large language models. 2025, arXiv preprint arXiv: 2503.09567

[155] Liu Y, Fan T, Chen T, Xu Q, Yang Q . FATE: an industrial grade platform for collaborative learning with data protection. The Journal of Machine Learning Research, 2021, 22( 1): 226

[156] Fan T, Kang Y, Ma G, Chen W, Wei W, Fan L, Yang Q. FATE-LLM: a industrial grade federated learning framework for large language models. 2023, arXiv preprint arXiv: 2310.10049

[157] Kuang W, Qian B, Li Z, Chen D, Gao D, Pan X, Xie Y, Li Y, Ding B, Zhou J. FederatedScope-LLM: a comprehensive package for fine-tuning large language models in federated learning. In: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 2024, 5260−5271

[158] Ye R, Wang W, Chai J, Li D, Li Z, Xu Y, Du Y, Wang Y, Chen S. OpenFedLLM: training large language models on decentralized private data via federated learning. In: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 2024, 6137−6147

[159] Jacob B, Kligys S, Chen B, Zhu M, Tang M, Howard A, Adam H, Kalenichenko D. Quantization and training of neural networks for efficient integer-arithmetic-only inference. In: Proceedings of 2018 IEEE Conference on Computer Vision and Pattern Recognition. 2018, 2704−2713

[160] Tong Y, Zeng Y, Song Y, Pan X, Fan Z, Xue C, Zhou Z, Zhang X, Chen L, Xu Y, Xu K, Lv W . Hu-Fu: efficient and secure spatial queries over data federation. The VLDB Journal, 2025, 34( 2): 19

[161] Tong Y, Pan X, Zeng Y, Shi Y, Xue C, Zhou Z, Zhang X, Chen L, Xu Y, Xu K, Lv W . Hu-Fu: efficient and secure spatial queries over data federation. Proceedings of the VLDB Endowment, 2022, 15( 6): 1159–1172

[162] BDA-Group. OpenHuFu-LLM. See Github.com/BUAA-BDA/OpenHufu-LLM website, 2025

[163] Dong H, Xie S. Large language models (LLMs): deployment, tokenomics and sustainability. 2024, arXiv preprint arXiv: 2405.17147

[164] Chen T, Kornblith S, Norouzi M, Hinton G. A simple framework for contrastive learning of visual representations. In: Proceedings of the 37th International Conference on Machine Learning. 2020, 1597−1607

[165] Lewis P, Perez E, Piktus A, Petroni F, Karpukhin V, Goyal N, Küttler H, Lewis M, Yih T W, Rocktäschel T, Riedel S, Kiela D. Retrieval-augmented generation for knowledge-intensive NLP tasks. In: Proceedings of the 34th International Conference on Neural Information Processing Systems. 2020, 793

[166] Jiang E. Clinical question-answering over distributed EHR data. Massachusetts Institute of Technology, Dissertation, 2024

[167] Guerraoui R, Kermarrec A M, Petrescu D, Pires R, Randl M, de Vos M. Efficient federated search for retrieval-augmented generation. In: Proceedings of the 5th Workshop on Machine Learning and Systems. 2025, 74−81

[168] Shojaee P, Harsha S S, Luo D, Maharaj A, Yu T, Li Y. Federated retrieval augmented generation for multi-product question answering. In: Proceedings of the 31st International Conference on Computational Linguistics: Industry Track. 2025, 387−397

[169] Yang M, Xu J, Ding W, Liu Y . FedHAP: federated hashing with global prototypes for cross-silo retrieval. IEEE Transactions on Parallel and Distributed Systems, 2024, 35( 4): 592–603

[170] Douze M, Guzhva A, Deng C, Johnson J, Szilvasy G, Mazaré P E, Lomeli M, Hosseini L, Jégou H. The Faiss library. 2025, arXiv preprint arXiv: 2401.08281

[171] Malkov Y A, Yashunin D A . Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42( 4): 824–836

RIGHTS & PERMISSIONS

The Author(s) 2025. This article is published with open access at link.springer.com and journal.hep.com.cn