API Usage Constraint Knowledge Construction Based on Large Language Model

doi:10.19678/j.issn.1000-3428.0070623

Abstract

Abstract:

Application Programming Interface (API) usage constraints are the conditions or restrictions that developers must follow when invoking APIs to ensure correct usage and prevent misuse. API documentation is an important tool for extracting these constraints. Existing Natural Language Processing (NLP)-based methods for extracting API usage constraints often rely on syntactic patterns, but their ability to handle complex coordinated sentences and impose strict requirements on syntactic structures is limited. To address these issues, this paper proposes an API usage constraint knowledge extraction method based on Large Language Model (LLM), referred to as AUCK. AUCK first preprocesses Java API documentation and extracts sentences containing API usage constraints. It then summarizes the syntactic patterns of coordinated sentences and designs corresponding cases to guide a LLM to decompose coordinated sentences into simple sentences. Finally, it summarizes the syntactic patterns of triplets and design cases to guide the LLM in extracting API usage constraint triplets. Experimental results on Java API documentation show that AUCK achieves an accuracy of 92.23% and recall of 93.14%, significantly outperforming existing methods, including DRONE (accuracy: 80.61%, recall: 86.81%), the mainstream triplet extraction tool OpenIE (accuracy: 76.92%, recall: 52.63%), and the large language model ChatGPT-3.5 (accuracy: 82.23%, recall: 67.71%). In addition, the application of AUCK to Android and Python API documentation verifies its good transferability.

Key words: Java API documentation, API usage constraint, Large Language Model (LLM), parallel sentence decomposition, triplet extraction, knowledge extraction

摘要：

API(Application Programming Interface)使用约束是开发者在调用API时必须遵守的条件或限制，以确保正确使用并避免API误用。API文档是提取这些约束的重要来源。现有的基于自然语言处理(NLP)的API使用约束提取方法通常依赖于句法模式，但对复杂并列句的处理能力有限，且对语法模式要求严格。为此，提出一种基于大语言模型(LLM)的API使用约束知识提取方法，记为AUCK。AUCK首先对Java API文档进行预处理，提取包含API使用约束的句子；其次，总结并列句的句法模式并设计相应案例，指导LLM将并列句拆分为简单句；最后，针对简单句总结出三元组句法模式，并设计案例指导LLM提取API使用约束三元组。实验结果表明，在Java API文档上，AUCK的准确率和召回率分别达到92.23%和93.14%，显著优于现有方法DRONE(准确率为80.61%，召回率为86.81%)、主流三元组提取工具OpenIE(准确率为76.92%，召回率为52.63%)以及大语言模型ChatGPT-3.5(准确率为82.23%，召回率为67.71%)。此外，将AUCK应用于Android和Python API文档的实验结果验证了其良好的迁移能力。

关键词: Java API文档, API使用约束, 大语言模型, 并列句拆解, 三元组提取, 知识提取

LIU Genhao, ZHANG Neng, ZHENG Zibin. API Usage Constraint Knowledge Construction Based on Large Language Model[J]. Computer Engineering, 2025, 51(8): 74-85.

刘根壕, 张能, 郑子彬. 基于大语言模型的API使用约束知识构建[J]. 计算机工程, 2025, 51(8): 74-85.

/ Recommend / Download Citations

URL: https://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0070623

https://www.ecice06.com/EN/Y2025/V51/I8/74

Figures/Tables 13

References 27

1	LIU M W, PENG X, MARCUS A, et al. Generating query-specific class API summaries[C]//Proceedings of the 27th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering. New York, USA: ACM Press, 2019: 120-130.
2	LI H W, LI S R, SUN J M, et al. Improving API caveats accessibility by mining API caveats knowledge graph[C]//Proceedings of the IEEE International Conference on Software Maintenance and Evolution (ICSME). Washington D. C., USA: IEEE Press, 2018: 183-193.
3	REN X, YE X, XING Z, et al. API-misuse detection driven by fine-grained API-constraint knowledge graph[C]//Proceedings of the 35th IEEE/ACM International Conference on Automated Software Engineering. Washington D. C., USA: IEEE Press, 2020: 461-472.
4	ZHOU Y , WANG C Z , YAN X , et al. Automatic detection and repair recommendation of directive defects in Java API documentation. IEEE Transactions on Software Engineering, 2020, 46 (9): 1004- 1023. doi: 10.1109/TSE.2018.2872971
5	ZHOU Y, YAN X, CHEN T L, et al. DRONE: a tool to detect and repair directive defects in Java APIs documentation[C]//Proceedings of the 41st IEEE/ACM International Conference on Software Engineering: Companion Proceedings (ICSE-Companion). Washington D. C., USA: IEEE Press, 2019: 115-118.
6	DUAN S, GUANG Y, BU W J, et al. A survey of named entity disambiguation in entity linking[C]//Proceedings of the 3rd International Conference on Intelligent Communications and Computing (ICC). Washington D. C., USA: IEEE Press, 2023: 296-303.
7	QIAO Z, ZHANG C, DU G. Improving cybersecurity named entity recognition with large language models[C]//Proceedings of the 6th International Conference on Software Engineering and Computer Science (CSECS). Washington D. C., USA: IEEE Press, 2023: 1-6.
8	LIU Y, LIU M W, PENG X, et al. Generating concept based API element comparison using a knowledge graph[C]//Proceedings of the 35th IEEE/ACM International Conference on Automated Software Engineering. New York, USA: ACM Press, 2020: 834-845.
9	YIN H, ZHENG Y H, SUN Y C, et al. An API learning service for inexperienced developers based on API knowledge graph[C]//Proceedings of the IEEE International Conference on Web Services (ICWS). Washington D. C., USA: IEEE Press, 2021: 251-261.
10	LIU M W , ZHAO C Y , PENG X , et al. Task-oriented ML/DL library recommendation based on a knowledge graph. IEEE Transactions on Software Engineering, 2023, 49 (8): 4081- 4096. doi: 10.1109/TSE.2023.3285280
11	ZHOU C. Intelligent bug fixing with software bug knowledge graph[C]//Proceedings of the 26th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering. New York, USA: ACM Press, 2018: 944-947.
12	CHENG X Q, SUN X B, BO L L, et al. KVS: a tool for knowledge-driven vulnerability searching[C]//Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering. New York, USA: ACM Press, 2022: 1731-1735.
13	LIU C W, CHEN S, FAN L L, et al. Demystifying the vulnerability propagation and its evolution via dependency trees in the NPM ecosystem[C]//Proceedings of the 44th International Conference on Software Engineering. New York, USA: ACM Press, 2022: 672-684.
14	JIANG Y J , LIU H , JIN J H , et al. Automated expansion of abbreviations based on semantic relation and transfer expansion. IEEE Transactions on Software Engineering, 2022, 48 (2): 519- 537. doi: 10.1109/TSE.2020.2995736
15	CHANG T Y, CHEN S Z, FAN G D, et al. A self-iteration code generation method based on large language models[C]//Proceedings of the 29th IEEE International Conference on Parallel and Distributed Systems (ICPADS). Washington D. C., USA: IEEE Press, 2023: 275-281.
16	HUANG T, SUN Z H, JIN Z, et al. Knowledge-aware code generation with large language models[C]//Proceedings of the 32nd IEEE/ACM International Conference on Program Comprehension. New York, USA: ACM Press, 2024: 52-63.
17	RAHMAN M T, SINGH R, SULTAN M Y. Automating patch set generation from code reviews using large language models[C]//Proceedings of the 3rd IEEE/ACM International Conference on AI Engineering-Software Engineering for AI. New York, USA: ACM Press, 2024: 273-274.
18	LIU Z H, LIAO Q, GU W C, et al. Software vulnerability detection with GPT and in-context learning[C]//Proceedings of the 8th International Conference on Data Science in Cyberspace (DSC). Washington D. C., USA: IEEE Press, 2023: 229-236.
19	LI Y, GUO J. Research on program automatic repair method combining context optimization strategy and large language models[C]//Proceedings of the 4th International Symposium on Computer Technology and Information Science. Washington D. C., USA: IEEE Press, 2024: 26-34.
20	BO L L, HE Y T, SUN X B, et al. A software bug fixing approach based on knowledge-enhanced large language models[C]//Proceedings of the 24th IEEE International Conference on Software Quality, Reliability and Security (QRS). Washington D. C., USA: IEEE Press, 2024: 169-179.
21	QI F, HOU Y, LIN N, et al. A survey of testing techniques based on large language models[C]//Proceedings of 2024 International Conference on Computer and Multimedia Technology. New York, USA: ACM Press, 2024: 280-284.
22	HOFFMANN J, FRISTER D. Generating software tests for mobile applications using fine-tuned large language models[C]//Proceedings of the 5th ACM/IEEE International Conference on Automation of Software Test (AST 2024). New York, USA: ACM Press, 2024: 76-77.
23	WU L X, ZHAO Y J, HOU X Y, et al. ChatGPT chats decoded: uncovering prompt patterns for superior solutions in software development lifecycle[C]//Proceedings of the 21st International Conference on Mining Software Repositories. New York, USA: ACM Press, 2024: 142-146.
24	SURI S, DAS S N, SINGI K, et al. Software engineering using autonomous agents: are we there yet?[C]//Proceedings of the 38th IEEE/ACM International Conference on Automated Software Engineering (ASE). Washington D. C., USA: IEEE Press, 2023: 1855-1857.
25	衡红军, 苗菁. 语义与句法信息加强的二元标记实体关系联合抽取. 计算机工程, 2023, 49 (4): 77- 84. doi: 10.19678/j.issn.1000-3428.0064545
	HENG H J , MIAO J . Joint extraction of binary tagging entity relation for enhanced semantic and syntactic information. Computer Engineering, 2023, 49 (4): 77- 84. doi: 10.19678/j.issn.1000-3428.0064545
26	李华昱, 张智康, 闫阳, 等. 基于知识图谱增强的领域多模态实体识别. 计算机工程, 2024, 50 (8): 31- 39. doi: 10.19678/j.issn.1000-3428.0068225
	LI H Y , ZHANG Z K , YAN Y , et al. Enhanced domain multi-modal entity recognition based on knowledge graph. Computer Engineering, 2024, 50 (8): 31- 39. doi: 10.19678/j.issn.1000-3428.0068225
27	吴韵巧. 基于Wilcoxon符号秩和检验的EEG信号相位滞后研究[D]. 南京: 东南大学, 2018.
	WU Y Q. Research on phase lag of EEG signals based on Wilcoxon signed-rank test[D]. Nanjing: Southeast University, 2018. (in Chinese)

[1]	HUANG Zipeng, ZENG Biqing, CHEN Pengfei, ZHOU Siying. Aspect Sentiment Triplet Extraction Based on Linguistic Feature Enhancement [J]. Computer Engineering, 2025, 51(6): 83-92.
[2]	Biqing ZENG, Pengfei CHEN, Yongtao YAO. Aspect Sentiment Triplet Extraction Combining Chain-of-Thought and Low-Rank Adaptation Fine-Tuning [J]. Computer Engineering, 2024, 50(7): 53-62.
[3]	WANG Haofen, DING Jun, HU Fanghuai, WANG Xin. Survey on Large Scale Enterprise-level Knowledge Graph Practices [J]. Computer Engineering, 2020, 46(7): 1-13.
[4]	WU Xiaofang,YANG Zhihao,LIN Hongfei,WANG Jian. Disease Knowledge Extraction System Based on Semantic Relation [J]. Computer Engineering, 2015, 41(1): 284-288.
[5]	YANG Zhi-Wei, YANG Ke-Wei, MAO Jie, TAN Ti-Jin. Capability Knowledge Management System in Equipment System Based on XML [J]. Computer Engineering, 2012, 38(3): 34-36.

Please choose a citation manager

Content to export