Page 242 - 《软件学报》2026年第6期

吴俊儒 等: 基于协作关系的模型动态路由 2561

Computing, 2025, 9(4): 87. [doi: 10.3390/bdcc9040087]
[6] Chang YP, Wang X, Wang JD, Wu Y, Yang LY, Zhu KJ, Chen H, Yi XY, Wang CX, Wang YD, Ye W, Zhang Y, Chang Y, Yu PS,
Yang Q, Xie X. A survey on evaluation of large language models. ACM Trans. on Intelligent Systems and Technology, 2024, 15(3): 39.
[doi: 10.1145/3641289]
[7] Yu Y, Zhuang YC, Zhang JY, Meng Y, Ratner A, Krishna R, Shen JM, Zhang C. Large language model as attributed training data
generator: A tale of diversity and bias. In: Proc. of the 37th Int’l Conf. on Neural Information Processing Systems. New Orleans: Curran
Associates Inc. , 2023. 55734–55784.
[8] Hajikhani A, Cole C. A critical review of large language models: Sensitivity, bias, and the path toward specialized AI. Quantitative
Science Studies, 2024, 5(3): 736–756. [doi: 10.1162/qss_a_00310]
[9] Wang YB, Wang Y, Yu Y, Xu C, Yu H, Zhu ZL. Insights and analysis of open-source license violation risks in LLMs generated code.
Ruan Jian Xue Bao/Journal of Software, 2025, 36(6): 2535–2557 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/
7324.htm [doi: 10.13328/j.cnki.jos.007324]
[10] Lin XY, Wang WJ, Li YQ, Yang S, Feng FL, Wei YW, Chua TS. Data-efficient fine-tuning for LLM-based recommendation. In: Proc. of
the 47th Int’l ACM SIGIR Conf. on Research and Development in Information Retrieval. Washington: ACM, 2024. 365–374. [doi: 10.
1145/3626772.3657807]
[11] DeepSeek-AI. DeepSeek-R1: Incentivizing reasoning capability in LLMs via reinforcement learning. arXiv:2501.12948, 2025.
[12] Yao HW, Lou J, Qin Z, Ren K. PromptCARE: Prompt copyright protection by watermark injection and verification. In: Proc. of the 2024
IEEE Symp. on Security and Privacy (SP). San Francisco: IEEE, 2024. 845–861. [doi: 10.1109/SP54263.2024.00209]
[13] Singhal K, Tu T, Gottweis J, et al. Toward expert-level medical question answering with large language models. Nature Medicine, 2025,
31(3): 943–950. [doi: 10.1038/s41591-024-03423-7]
[14] Gao YF, Yu DQ, Wang SQ, Wang HF. Large language model powered site selection recommender system. Journal of Computer
Research and Development, 2024, 61(7): 1681–1696 (in Chinese with English abstract). [doi: 10.7544/issn1000-1239.202330629]
[15] Hazell J. Spear phishing with large language models. arXiv:2305.06972, 2023.
[16] Yuan Z, Yuan HY, Li CP, Dong GT, Lu KM, Tan CQ, Zhou C, Zhou JR. Scaling relationship on learning mathematical reasoning with
large language models. arXiv:2308.01825, 2023.
[17] He XW, Lin ZH, Gong YY, Jin AL, Zhang H, Chen L, Jiao J, Yiu SM, Duan N, Chen WZ. AnnoLLM: Making large language models to
be better crowdsourced annotators. In: Proc. of the 2024 Conf. of the North American Chapter of the Association for Computational
Linguistics: Human Language Technologies, Vol. 6 (Industry Track). Mexico City: ACL, 2024. 165–190. [doi: 10.18653/v1/2024.naacl-
industry.15]
[18] Lan YQ, Rao Y, Li GC, Sun L, Xia BC, Xin TT. A survey of text generation and evaluation based on intrinsic quality constraints. Acta
Electronica Sinica, 2024, 52(2): 633–659 (in Chinese with English abstract). [doi: 10.12263/DZXB.20230826]
[19] Wu YQ, Zhou SY, Liu YF, Lu WM, Liu XZ, Zhang YT, Sun CL, Wu F, Kuang K. Precedent-enhanced legal judgment prediction with
LLM and domain-model collaboration. In: Proc. of the 2023 Conf. on Empirical Methods in Natural Language Processing. Singapore:
ACL, 2023. 12060–12075. [doi: 10.18653/v1/2023.emnlp-main.740]
[20] Barbosa R, Santos R, Novais P. Collaborative problem-solving with LLM: A multi-agent system approach to solve complex tasks using
Autogen. In: Proc. of the 2025 Int’l Conf. on Highlights in Practical Applications of Agents, Multi-agent Systems, and Digital Twins: The
PAAMS Collection. Salamanca: Springer, 2025. 203–214. [doi: 10.1007/978-3-031-73058-0_17]
[21] Lan XC, Gao C, Jin DP, Li Y. Stance detection with collaborative role-infused LLM-based agents. In: Proc. of the 18th Int’l AAAI Conf.
on Web and Social Media. Buffalo: AAAI, 2024. 891–903. [doi: 10.1609/icwsm.v18i1.31360]
[22] Weng YX, Wu GQ, Zheng TY, Yang YB, Luo J. Large model for small data: Foundation model for cross-modal RF human activity
recognition. In: Proc. of the 22nd ACM Conf. on Embedded Networked Sensor Systems. Hangzhou: ACM, 2024. 436–449. [doi: 10.1145/
3666025.3699349]
[23] Ge B, He CH, Zhang C, Xu H, Hu SZ. Unified transformation framework of open tag feature for Chinese multi-modal data. In: Proc. of
the 9th Int’l Conf. on Big Data and Information Analytics (BigDIA). Haikou: IEEE, 2023. 692–698. [doi: 10.1109/BigDIA60676.2023.
10429510]
[24] Zhang Y, Feng FL, Zhang JZ, Bao KQ, Wang QF, He XN. CoLLM: Integrating collaborative embeddings into large language models for
recommendation. IEEE Trans. on Knowledge and Data Engineering, 2025, 37(5): 2329–2340. [doi: 10.1109/TKDE.2025.3540912]
[25] Tang YW, Zhang R, Liu JM, Guo Z, Zhao B, Wang ZG, Gao P, Li HS, Wang D, Li XL. Any2Point: Empowering any-modality large
models for efficient 3D understanding. In: Proc. of the 18th European Conf. on Computer Vision. Milan: Springer, 2025. 456–473. [doi:
10.1007/978-3-031-72764-1_26]