基于大语言模型的Web文本输入组件测试方法

张亚东; 崔展齐; 兰文尉; 徐伟利; 曹鹤玲

doi:10.12263/DZXB.20250880

您当前的位置：

首页 >

文章列表页 >

基于大语言模型的Web文本输入组件测试方法

学术论文 | 更新时间：2026-04-29

- 基于大语言模型的Web文本输入组件测试方法
- Testing Text Input Components of Web Applications Based on Large Language Models
- 电子学报 2026年54卷第1期页码：276-290
- 作者机构：
  
  1.北京信息科技大学计算机学院，北京 100192
  2.河南工业大学信息科学与工程学院，河南郑州 450001
- 作者简介：
  
  [ "张亚东男，2002年2月生。山东济宁人。现为北京信息科技大学硕士研究生。主要研究方向为软件分析及软件测试技术。E-mail: zhangyadong@bistu.edu.cn" ]
  [ "崔展齐男，1984年2月生。贵州金沙人。现为北京信息科技大学教授、博士生导师。主要研究方向为软件分析及软件测试技术。E-mail: czq@bistu.edu.cn" ]
  [ "兰文尉男，1999年6月生。北京人。硕士毕业于北京信息科技大学。主要研究方向为软件分析及软件测试技术。E-mail: lww_lowry@bistu.edu.cn" ]
  [ "徐伟利男，2002年2月生。天津人。现为北京信息科技大学硕士研究生。主要研究方向为智能化软件工程。E-mail: weili_xu@bistu.edu.cn" ]
  [ "曹鹤玲女，1980年5月生。河南南阳人。现为河南工业大学教授、博士生导师。主要研究方向为软件缺陷定位、软件缺陷修复和深度学习技术。E-mail: caohl@haut.edu.cn" ]
- 基金信息：
  
  江苏省前沿引领技术基础研究专项(BK20202001);北京信息科技大学“勤信人才”培育计划项目(QXTCP B202406)
- DOI：10.12263/DZXB.20250880
  中图分类号： TP311.5;
- 收稿：2025-12-31，
  
  录用：2026-01-13，
  
  纸质出版：2026-01-25
- 稿件说明：
移动端阅览
张亚东, 崔展齐, 兰文尉, 等. 基于大语言模型的Web文本输入组件测试方法[J]. 电子学报, 2026, 54(01): 276-290.

ZHANG Yadong, CUI Zhanqi, LAN Wenwei, et al. Testing Text Input Components of Web Applications Based on Large Language Models[J]. Acta Electronica Sinica, 2026, 54(01): 276-290.
张亚东, 崔展齐, 兰文尉, 等. 基于大语言模型的Web文本输入组件测试方法[J]. 电子学报, 2026, 54(01): 276-290. DOI：10.12263/DZXB.20250880

ZHANG Yadong, CUI Zhanqi, LAN Wenwei, et al. Testing Text Input Components of Web Applications Based on Large Language Models[J]. Acta Electronica Sinica, 2026, 54(01): 276-290. DOI：10.12263/DZXB.20250880

摘要

文本输入组件是Web应用实现交互功能的重要组成部分，广泛应用于搜索查询、内容创作等操作场景，其输入内容通常受到语法和复杂业务规则的约束。若文本输入组件未能正确处理恶意或非预期的文本输入，可能导致应用崩溃。现有的Web图形用户界面（Graphical User Interface，GUI）测试工具未能充分考虑文本输入组件的约束关系，无法生成具有针对性的文本输入来检测应用中文本输入组件的错误。此外，现有方法通常忽略了多个文本输入组件之间还可能存在复杂的约束关系，难以生成多样化的文本输入组合。为此，本文提出了一种基于大语言模型（Large Language Models，LLMs）的Web应用文本输入组件测试方法LTICT（LLM-based Text Input Component Testing）。首先，LTICT从被测应用的HTML文件中提取文本输入组件的信息，以供LLM推断文本输入组件的约束关系，并据此引导LLM合成程序；然后，LTICT执行该程序来批量生成文本输入，以对文本输入组件进行测试；最后，LTICT将收集所测试文本输入组件的上下文信息和所生成测试数据的执行结果，反馈给LLM以帮助其分析多个文本输入组件间的约束关系，从而生成更多样化的文本输入组合。在4个开源Web应用上进行的实验结果表明，相比于广泛使用的自动化测试工具WebExplor、DBInputs、QTypist，LTICT检测文本输入组件错误的数量分别提升了34.21%、37.84%和8.51%。在检测文本输入组件错误的平均用时方面，LTICT比WebExplor、DBInputs、QTypist分别减少了10.69%、11.87%和6.99%。

Abstract

Text input components are essential to Web applications and are widely used in scenarios such as search queries and content creation. Their inputs are typically constrained by syntactic rules and complex business logics. If text input components fail to correctly handle malicious or unexpected input texts

they may cause application crashes. Existing automated graphical user interface (GUI) testing tools for web applications often ignore these constraints. As a result

they cannot generate diverse inputs to effectively detect faults of text input components. Moreover

existing methods often overlook complex constraints among multiple text input components

which makes it difficult to generate diverse input combinations. To address this issue

this paper proposes an approach for testing text input components of web applications based on large language models (LLMs)

named LLM-based text input component testing (LTICT). First

LTICT extracts information about text input components from the HTML files of the application under test. It then uses a LLM to infer the constraints of the text input components and to synthesize a text generation program with respect to these constraints. Next

LTICT executes the program to produce input texts in batches to test text input components. Finally

LTICT feeds component contexts and execution outcomes back to the LLM. These feedbacks help the LLM to analyze inter-component constraints and to generate more diverse combinations of inputs. To evaluate the effectiveness of LTICT

comparative experiments are conducted on four open-source web applications with three automated testing tools

which are WebExplor

DBInputs

and QTypist. The experimental results show that LTICT detects more text input component faults

with improvements of 34.21%

37.84%

and 8.51% over WebExplor

DBInputs

and QTypist

respectively. In addition

LTICT reduces the average time required to detect text input component faults by 10.69%

11.87%

and 6.99%

respectively.

关键词

Keywords

references

Liu Zhe , Chen Chunyang , Wang Junjie , et al . Testing the limits: Unusual text inputs generation for mobile app crash detection with large language model [C ] // Proceedings of the IEEE/ACM 46th International Conference on Software Engineering . New York : ACM , 2024 : 1 - 12 .

Wang Siyi , Wang Sinan , Fan Yujia , et al . Leveraging large vision-language model for better automatic web GUI testing [C ] // 2024 IEEE International Conference on Software Maintenance and Evolution . Piscataway : IEEE , 2024 : 125 - 137 .

Liu Zhe , Chen Chunyang , Wang Junjie , et al . Fill in the blank: Context-aware automated text input generation for mobile GUI testing [C ] // 2023 IEEE/ACM 45th International Conference on Software Engineering . Piscataway : IEEE , 2023 : 1355 - 1367 .

Clerissi D , Denaro G , Mobilio M , et al . Plug the database & play with automatic testing: Improving system testing by exploiting persistent data [C ] // Proceedings of the 35th IEEE/ACM International Conference on Automated Software Engineering . New York : ACM , 2021 : 66 - 77 .

Sherin S , Muqeet A , Khan M U , et al . QExplore: An exploration strategy for dynamic web applications using guided search [J ] . Journal of Systems and Software , 2023 , 195 : 111512 .

Zheng Yan , Liu Yi , Xie Xiaofei , et al . Automatic web testing using curiosity-driven reinforcement learning [C ] // 2021 IEEE/ACM 43rd International Conference on Software Engineering . Piscataway : IEEE , 2021 : 423 - 435 .

Clerissi D , Denaro G , Mobilio M , et al . DBInputs: Exploiting persistent data to improve automated GUI testing [J ] . IEEE Transactions on Software Engineering , 2024 , 50 ( 9 ): 2412 - 2436 .

许婷 , 肖桐 , 张圣林 , 等 . 基于LLM的日志故障诊断 [J ] . 电子学报 , 2025 , 53 ( 4 ): 1123 - 1141 .

Xu Ting , Xiao Tong , Zhang Shenglin , et al . Log fault diagnosis based on large language models [J ] . Acta Electronica Sinica , 2025 , 53 ( 4 ): 1123 - 1141 . (in Chinese)

Azzam F , Saies A , Jaber M , et al . Evaluation for web GUI automation testing tool - experiment [C ] // 2022 International Symposium on Multidisciplinary Studies and Innovative Technologies . Piscataway : IEEE , 2022 : 549 - 554 .

Mattiello G R , Endo A T . Model-based testing leveraged for automated web tests [J ] . Software Quality Journal , 2022 , 30 ( 3 ): 621 - 649 .

Biagiola M , Stocco A , Ricca F , et al . Diversity-based web test generation [C ] // Proceedings of the 2019 27th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering . New York : ACM , 2019 : 142 - 153 .

Biagiola M , Ricca F , Tonella P . Search based path and input data generation for web application testing [C ] // Search Based Software Engineering . Cham : Springer , 2017 : 18 - 32 .

Mariani L , Pezzè M , Riganelli O , et al . Link: Exploiting the web of data to generate test inputs [C ] // Proceedings of the 2014 International Symposium on Software Testing and Analysis . New York : ACM , 2014 : 373 - 384 .

Google . UI/application exerciser monkey [EB/OL ] . ( 2025-07-27 )[ 2025-09-30 ] . https://developer.android.com/studio/test/monkey https://developer.android.com/studio/test/monkey .

Li Yuanchun , Yang Ziyue , Guo Yao , et al . DroidBot: A lightweight UI-Guided test input generator for Android [C ] // 2017 IEEE/ACM 39th International Conference on Software Engineering Companion . Piscataway : IEEE , 2017 : 23 - 26 .

He Yuyu , Zhang Lei , Yang Zhemin , et al . TextExerciser: Feedback-driven text input exercising for Android applications [C ] // 2020 IEEE Symposium on Security and Privacy . Piscataway : IEEE , 2020 : 1071 - 1087 .

Alian P , Nashid N , Shahbandeh M , et al . Semantic constraint inference for web form test generation [C ] // Proceedings of the 33rd ACM SIGSOFT International Symposium on Software Testing and Analysis . New York : ACM , 2024 : 932 - 944 .

Liu Zhe , Chen Chunyang , Wang Junjie , et al . Make LLM a testing expert: Bringing human-like interaction to mobile GUI testing via functionality-aware decisions [C ] // Proceedings of the IEEE/ACM 46th International Conference on Software Engineering . New York : ACM , 2024 : 1 - 13 .

Le T , Tran T , Cao D , et al . KAT: Dependency-aware automated API testing with large language models [C ] // 2024 IEEE Conference on Software Testing, Verification and Validation . Piscataway : IEEE , 2024 : 82 - 92 .

Chen Jizheng , Du Kounianhua , Dai Xinyi , et al . DebateCoder: Towards collective intelligence of LLMs via test case driven LLM debate for code generation [C ] // Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics . Stroudsburg : ACL , 2025 : 12055 - 12065 .

Guo Yaoqi , Chen Zhenpeng , Zhang J M , et al . Personality-guided code generation using large language models [C ] // Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics . Stroudsburg : ACL , 2025 : 1068 - 1080 .

Alian P , Nashid N , Shahbandeh M , et al . Feature-driven end-to-end test generation [C ] // 2025 IEEE/ACM 47th International Conference on Software Engineering . Piscataway : IEEE , 2025 : 450 - 462 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于信息融合的区块链系统隐匿安全补丁识别及迁移技术

基于大语言模型语义增强的多模态智能合约漏洞检测方法研究

融合大语言模型与跨域图结构的多模态对话情感识别方法

大语言模型驱动下基于零样本语境联想的意图分类