Page 251 - 《软件学报》2026年第5期

2130 软件学报 2026 年第 37 卷第 5 期

[36] Wei J, Wang XZ, Schuurmans D, Bosma M, Ichter B, Xia F, Chi EH, Le QV, Zhou D. Chain-of-thought prompting elicits reasoning in
large language models. In: Proc. of the 36th Int’l Conf. on Neural Information Processing Systems. New Orleans: Curran Associates Inc.,
2022. 24824–24837.
[37] Bian N, Han XP, Sun L, Lin HY, Lu YJ, He B, Jian SS, Dong B. ChatGPT is a knowledgeable but inexperienced solver: An investigation
of commonsense problem in large language models. arXiv:2303.16421, 2024.
[38] Yang K, Tian YD, Peng NY, Klein D. Re3: Generating longer stories with recursive reprompting and revision. In: Proc. of the 2022 Conf.
on Empirical Methods in Natural Language Processing. Abu Dhabi: ACL, 2022. 4393–4479. [doi: 10.18653/v1/2022.emnlp-main.296]
[39] Min BN, Ross H, Sulem E, Ben Veyseh AP, Nguyen TH, Sainz O, Agirre E, Heintz I, Roth D. Recent advances in natural language
processing via large pre-trained language models: A survey. ACM Computing Surveys, 2023, 56(2): 30 [doi: 10.1145/3605943]
[40] Liu X, Ji KX, Fu YC, Tam W, Du ZX, Yang ZL, Tang J. P-tuning: Prompt tuning can be comparable to fine-tuning across scales and
tasks. In: Proc. of the 60th Annual Meeting of the Association for Computational Linguistics (Vol. 2: Short Papers). Dublin: ACL, 2022.
61–68. [doi: 10.18653/v1/2022.acl-short.8]
[41] Liu PF, Yuan WZ, Fu JL, Jian ZB, Hayashi H, Neubig G. Pre-train, prompt, and predict: A systematic survey of prompting methods in
natural language processing. ACM Computing Surveys, 2023, 55(9): 195 [doi: 10.1145/3560815]
[42] OpenAI. Introducing ChatGPT. 2022. https://openai.com/blog/chatgpt
[43] Zhao ZH, Wallace E, Feng S, Klein D, Singh S. Calibrate before use: Improving few-shot performance of language models. In: Proc. of
the 38th Int’l Conf. on Machine Learning. PMLR, 2021. 12697–12706.
[44] Su HJ, Kasai J, Wu CH, Shi WJ, Wang TL, Xin JY, Zhang R, Ostendorf M, Zettlemoyer L, Smith NA, Yu T. Selective annotation makes
language models better few-shot learners. arXiv:2209.01975, 2022.
[45] Liu JC, Shen DH, Zhang YZ, Dolan B, Carin L, Chen WZ. What makes good in-context examples for GPT-3? In: Proc. of the 3rd
Workshop on Knowledge Extraction and Integration for Deep Learning Architectures. Dublin: ACL, 2022. 100–114. [doi: 10.18653/v1/
2022.deelio-1.10]
[46] Trajanoska M, Stojanov R, Trajanov D. Enhancing knowledge graph construction using large language models. arXiv:2305.04676, 2023.
[47] Kommineni VK, König-Ries B, Samuel S. From human experts to machines: An LLM supported approach to ontology and knowledge
graph construction. arXiv:2403.08345, 2024.
[48] Carta S, Giuliani A, Piano L, Podda AS, Pompianu L, Tiddia SG. Iterative zero-shot LLM prompting for knowledge graph construction.
arXiv:2307.01128, 2023.
[49] PostgreSQL global development group. PostgreSQL 12.22 documentation. 2024. https://www.postgresql.org/docs/12/
[50] Facebook. Faiss. 2024. https://github.com/facebookresearch/faiss
[51] OpenAI. GPT-4o-mini: Advancing cost-efficient intelligence. 2024. https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-
intelligence/
[52] OpenAI. GPT-4o. 2024. https://openai.com/index/hello-gpt-4o/
[53] Soot. Soot—A framework for analyzing and transforming Java and Android applications. 2024. https://soot-oss.github.io/soot/
[54] Apache Hadoop. HDFS Architecture. 2018. https://hadoop.apache.org/docs/r2.9.2/hadoop-project-dist/hadoop-hdfs/HdfsDesign.html
[55] Apache Hadoop. HDFS-default.xml. 2018. https://hadoop.apache.org/docs/r2.9.2/hadoop-project-dist/hadoop-hdfs/hdfs-default.xml

附中文参考文献
[5] 腾讯云. 腾讯云 4 月 8 日故障复盘及情况说明. 2024. https://cloud.tencent.com/developer/article/2408984
[10] 周书林, 李姗姗, 董威, 王戟, 廖湘科. 软件运行时配置研究综述. 软件学报, 2024, 35(1): 63–86. http://www.jos.org.cn/1000-9825/6835.
htm [doi: 10.13328/j.cnki.jos.006835]

作者简介
张添翼, 硕士生, 主要研究领域为云原生, 智能化运维.
周彤, 博士生, 主要研究领域为云原生, 智能化运维.
张晨曦, 博士, 副教授, CCF 专业会员, 主要研究领域为智能化运维, 云原生, 软件测试.
彭鑫, 博士, 教授, 博士生导师, CCF 杰出会员, 主要研究领域为智能化软件开发, 云原生, 智能化运维, 泛在计算软件系统.