[{"data":1,"prerenderedAt":369},["ShallowReactive",2],{"publication-2025\u002Flarge-language-models-for-automated-web-form-test-generation-an-empirical-study-en":3,"publication-members":56},{"_path":4,"_dir":5,"_draft":6,"_partial":6,"_locale":7,"title":8,"description":9,"_hidden":6,"Study\" authors":10,"authors_orcid":16,"year":22,"doi":23,"openalex_id":24,"venue":25,"abstract_screenshot":26,"keywords":27,"body":36,"_type":49,"_id":50,"_source":51,"_file":52,"_stem":53,"_extension":54,"locale":55},"\u002Fpublications\u002F2025\u002Flarge-language-models-for-automated-web-form-test-generation-an-empirical-study","2025",false,"","Large Language Models for Automated Web-Form-Test Generation: An Empirica","Testing web forms is an essential activity for ensuring the quality of web applications. It typically involves evaluating the interactions between users and forms. Automated test-case generation remains a challenge for web-form testing: Due to the complex, multi-level structure of Web pages, it can be difficult to automatically capture their inherent contextual information for inclusion in the tests. Large Language Models (LLMs) have shown great potential for contextual text generation. This motivated us to explore how they could generate automated tests for web forms, making use of the contextual information within form elements. To the best of our knowledge, no comparative study examining different LLMs has yet been reported for web-form-test generation. To address this gap in the literature, we conducted a comprehensive empirical study investigating the effectiveness of 11 LLMs on 146 web forms from 30 open source Java web applications. In addition, we propose three HTML-structure-pruning methods to extract key contextual information. The experimental results show that different LLMs can achieve different testing effectiveness, with the GPT-4, GLM-4, and Baichuan2 LLMs generating the best web-form tests. Compared with GPT-4, the other LLMs had difficulty generating appropriate tests for the web forms: Their Successfully Submitted Rates (SSRs)—the proportions of the LLMs-generated web-form tests that could be successfully inserted into the web forms and submitted—decreased by 9.10% to 74.15%. Our findings also show that, for all LLMs, when the designed prompts include complete and clear contextual information about the web forms, more effective web-form tests were generated. Specifically, when using Parser-Processed HTML for Task Prompt (PH-P), the SSR averaged 70.63%, higher than the 60.21% for Raw HTML for Task Prompt (RH-P) and 50.27% for LLM-Processed HTML for Task Prompt (LH-P). With RH-P, GPT-4’s SSR was 98.86%, outperforming models like LLaMa2 (7B) with 34.47% and GLM-4V with 0%. Similarly, with PH-P, GPT-4 reached an SSR of 99.54%, the highest among all models and prompt types. Finally, this article also highlights strategies for selecting LLMs based on performance metrics, and for optimizing the prompt design to improve the quality of the web-form tests.",[11,12,13,14,15],"Li, Tao","Cui, Chenhui","Huang, Rubing","Towey, Dave","Ma, Lei",[17,18,19,20,21],"0009-0001-7413-9692","0009-0004-8746-316X","0000-0002-1769-6126","0000-0003-0877-4353","0000-0002-8621-2420",2025,"https:\u002F\u002Fdoi.org\u002F10.1145\u002F3735553","W4410344404","ACM Transactions on Software Engineering and Methodology",null,[28,29,30,31,32,33,34,35],"Computer science","Test (biology)","Software engineering","Web application","Natural language processing","Programming language","World Wide Web","Information retrieval",{"type":37,"children":38,"toc":46},"root",[39],{"type":40,"tag":41,"props":42,"children":43},"element","p",{},[44],{"type":45,"value":9},"text",{"title":7,"searchDepth":47,"depth":47,"links":48},2,[],"markdown","content:publications:2025:large-language-models-for-automated-web-form-test-generation-an-empirical-study.md","content","publications\u002F2025\u002Flarge-language-models-for-automated-web-form-test-generation-an-empirical-study.md","publications\u002F2025\u002Flarge-language-models-for-automated-web-form-test-generation-an-empirical-study","md","en",[57,70,75,86,93,101,107,116,123,129,134,144,151,160,166,178,187,196,202,210,215,223,229,237,241,251,258,266,271,280,286,294,300,308,313,319,329,337,343,351,356,364],{"_path":58,"title":59,"name":60,"role":61,"email":26,"image":62,"category":63,"interests":64,"order":47,"_id":69},"\u002Fmembers\u002Fstaff\u002Falain-chong","Vice President for Global Affairs and Partnerships · Professor of Information Systems and Digital Innovation","Alain Chong","Deputy Director of Lab","assets\u002F8.png","staff",[65,66,67,68],"信息系统与运作管理","计算机科学与运筹学","Information Systems and Operations Management","Computer Science and Operations Research","content:members:staff:alain-chong.md",{"_path":58,"title":71,"role":72,"interests":73,"_id":74},"全球事务与合作副校长 · 信息系统与数字创新教授","实验室副主任",[65,66],"content:members:staff:alain-chong.zh-CN.md",{"_path":76,"title":77,"name":78,"role":79,"email":26,"image":80,"category":63,"interests":81,"order":84,"_id":85},"\u002Fmembers\u002Fstaff\u002Fanthony-belloti","Professor","Anthony Belloti","Core Member","assets\u002F41.png",[82,83],"Machine Learning and Credit Risk Model","Model Risks",9,"content:members:staff:anthony-belloti.md",{"_path":76,"title":87,"role":88,"interests":89,"_id":92},"计算机科学系教授","核心成员",[90,91],"机器学习与信用风险模型","模型风险","content:members:staff:anthony-belloti.zh-CN.md",{"_path":94,"title":95,"name":95,"role":79,"email":26,"image":96,"category":63,"interests":97,"order":99,"_id":100},"\u002Fmembers\u002Fstaff\u002Fboon-giin-lee","Boon Giin Lee","assets\u002F31.jpg",[98],"Intelligent Sensor and Extended Reality",11,"content:members:staff:boon-giin-lee.md",{"_path":94,"title":102,"role":88,"interests":103,"_id":106},"人机交互实验室负责人 · 计算机科学系副教授",[104,105],"人机交互 HCI","智能传感与扩展现实技术","content:members:staff:boon-giin-lee.zh-CN.md",{"_path":108,"title":109,"name":109,"role":110,"email":26,"image":111,"category":63,"interests":112,"order":114,"_id":115},"\u002Fmembers\u002Fstaff\u002Fcong-cao","Cong Cao","Direction Leader","assets\u002FCC.png",[113],"Science and technology policy and institutional reform",7,"content:members:staff:cong-cao.md",{"_path":108,"title":117,"name":118,"role":119,"interests":120,"_id":122},"宁波诺丁汉大学商学院创新学教授","曹聪","方向带头人",[121],"科技政策与体制改革","content:members:staff:cong-cao.zh-CN.md",{"_path":124,"title":125,"name":125,"role":79,"email":26,"image":126,"category":63,"order":127,"_id":128},"\u002Fmembers\u002Fstaff\u002Fdave-towey","Dave Towey","assets\u002F32.jpg",8,"content:members:staff:dave-towey.md",{"_path":124,"title":130,"role":88,"interests":131,"_id":133},"计算机科学系教授 · 计算机科学系主任",[132],"计算机科学与语言学","content:members:staff:dave-towey.zh-CN.md",{"_path":135,"title":136,"name":136,"role":79,"email":26,"image":137,"category":63,"interests":138,"order":142,"_id":143},"\u002Fmembers\u002Fstaff\u002Ffazl-ullah-khan","Fazl Ullah Khan","assets\u002F44.png",[139,140,141],"Computer Network","Computer Architecture and Network Security","Software Engineering",12,"content:members:staff:fazl-ullah-khan.md",{"_path":135,"title":145,"role":88,"interests":146,"_id":150},"计算机科学系助理教授 · IEEE 高级会员",[147,148,149],"计算机网络","计算机和网络安全","软件工程","content:members:staff:fazl-ullah-khan.zh-CN.md",{"_path":152,"title":153,"name":154,"role":79,"email":26,"image":155,"category":63,"interests":156,"order":158,"_id":159},"\u002Fmembers\u002Fstaff\u002Fheng-yu","Associate Professor","Heng Yu","assets\u002FHENGYU.png",[157],"Embedded Systems Design",17,"content:members:staff:heng-yu.md",{"_path":152,"title":161,"name":162,"role":88,"interests":163,"_id":165},"计算机科学系副教授","于恒",[164],"嵌入式系统设计","content:members:staff:heng-yu.zh-CN.md",{"_path":167,"title":153,"name":168,"role":79,"email":26,"image":169,"category":63,"interests":170,"order":176,"_id":177},"\u002Fmembers\u002Fstaff\u002Fheshan-du","Heshan Du","assets\u002Fhesahndu.png",[171,172,173,174,175],"Logic, Knowledge Representation and Reasoning","Geographic Information Systems","Operations Research","Machine Learning","Reinforcement Learning",20,"content:members:staff:heshan-du.md",{"_path":167,"title":161,"name":179,"role":88,"interests":180,"_id":186},"杜何珊",[181,182,183,184,185],"逻辑与知识表示","地理信息系统","运筹学","机器学习","强化学习","content:members:staff:heshan-du.zh-CN.md",{"_path":188,"title":189,"name":190,"role":79,"email":26,"image":191,"category":63,"interests":192,"order":194,"_id":195},"\u002Fmembers\u002Fstaff\u002Fhuan-jin","Assistant Professor","Huan Jin","assets\u002Fhuanjin.png",[193,174],"Optimisation",21,"content:members:staff:huan-jin.md",{"_path":188,"title":197,"name":198,"role":88,"interests":199,"_id":201},"计算机科学系助理教授","靳欢",[200,184],"优化","content:members:staff:huan-jin.zh-CN.md",{"_path":203,"title":153,"name":204,"role":110,"email":26,"image":205,"category":63,"interests":206,"order":208,"_id":209},"\u002Fmembers\u002Fstaff\u002Fjianfeng-ren","Jianfeng Ren","assets\u002F42.jpg",[174,207],"Computer Vision",3,"content:members:staff:jianfeng-ren.md",{"_path":203,"title":161,"name":211,"role":119,"interests":212,"_id":214},"任剑锋",[184,213],"计算机视觉","content:members:staff:jianfeng-ren.zh-CN.md",{"_path":216,"title":217,"name":217,"role":110,"email":26,"image":218,"category":63,"interests":219,"order":221,"_id":222},"\u002Fmembers\u002Fstaff\u002Fjiawei-li","Jiawei Li","assets\u002F11.png",[220],"Computer Science and Artificial Intelligence",15,"content:members:staff:jiawei-li.md",{"_path":216,"title":224,"name":225,"role":119,"interests":226,"_id":228},"计算机科学系助理教授 · 英国诺丁汉大学博士后","李家炜",[227],"计算机与人工智能","content:members:staff:jiawei-li.zh-CN.md",{"_path":230,"title":153,"name":231,"role":79,"email":26,"image":232,"category":63,"interests":233,"order":235,"_id":236},"\u002Fmembers\u002Fstaff\u002Fmatthew-pike","Matthew Pike","assets\u002F43.jpg",[234],"Digitalised Learning",16,"content:members:staff:matthew-pike.md",{"_path":230,"title":161,"role":88,"interests":238,"_id":240},[239],"数字化学习","content:members:staff:matthew-pike.zh-CN.md",{"_path":242,"title":189,"name":243,"role":79,"email":26,"image":244,"category":63,"interests":245,"order":249,"_id":250},"\u002Fmembers\u002Fstaff\u002Fning-xue","Ning Xue","\u002Fimages\u002Fuon-logo.png",[246,247,248],"Artificial Intelligence","Computational Intelligence","Combinatorial Optimization",13,"content:members:staff:ning-xue.md",{"_path":242,"title":197,"name":252,"role":88,"interests":253,"_id":257},"薛宁",[254,255,256],"人工智能","计算智能","组合优化","content:members:staff:ning-xue.zh-CN.md",{"_path":259,"title":189,"name":260,"role":79,"email":26,"image":261,"category":63,"interests":262,"order":264,"_id":265},"\u002Fmembers\u002Fstaff\u002Fqian-zhang","Qian Zhang","assets\u002Fqz.png",[263,207,174],"Image Processing",14,"content:members:staff:qian-zhang.md",{"_path":259,"title":197,"name":267,"role":88,"interests":268,"_id":270},"张茜",[269,213,184],"图像处理","content:members:staff:qian-zhang.zh-CN.md",{"_path":272,"title":77,"name":273,"role":274,"email":26,"image":275,"category":63,"interests":276,"orcid":277,"order":278,"_id":279},"\u002Fmembers\u002Fstaff\u002Fruibin-bai","Ruibin Bai","Director of Lab","assets\u002F38.png",[68],"0000-0003-1722-568X",1,"content:members:staff:ruibin-bai.md",{"_path":272,"title":281,"name":282,"role":283,"interests":284,"_id":285},"教授","白瑞斌","实验室主任",[66],"content:members:staff:ruibin-bai.zh-CN.md",{"_path":287,"title":288,"name":288,"role":110,"email":26,"image":289,"category":63,"interests":290,"order":292,"_id":293},"\u002Fmembers\u002Fstaff\u002Fsean-he","Sean He","assets\u002F39.png",[207,291,174],"Data Analytics",5,"content:members:staff:sean-he.md",{"_path":287,"title":295,"name":296,"role":119,"interests":297,"_id":299},"计算机科学系教授 · 国家级讲席学者","何祥健",[213,298,184],"数据分析","content:members:staff:sean-he.zh-CN.md",{"_path":301,"title":302,"name":302,"role":79,"email":26,"image":303,"category":63,"interests":304,"order":306,"_id":307},"\u002Fmembers\u002Fstaff\u002Ftianxiang-cui","Tianxiang Cui","assets\u002Ftianxiangcui.png",[247,305,174,175],"Operation Research",19,"content:members:staff:tianxiang-cui.md",{"_path":301,"title":145,"name":309,"role":88,"interests":310,"_id":312},"崔天翔",[255,311,184,185],"运筹研究","content:members:staff:tianxiang-cui.zh-CN.md",{"_path":314,"title":77,"name":315,"role":79,"email":26,"image":316,"category":63,"order":317,"_id":318},"\u002Fmembers\u002Fstaff\u002Fxiuping-hua","Xiuping Hua","assets\u002FxiupignHua.png",10,"content:members:staff:xiuping-hua.md",{"_path":314,"title":320,"name":321,"role":88,"interests":322,"_id":328},"金融、会计与经济系教授","华秀萍",[323,324,325,326,327,90],"资产定价","公司金融","衍生品","金融科技","创新金融和普惠金融","content:members:staff:xiuping-hua.zh-CN.md",{"_path":330,"title":77,"name":331,"role":79,"email":26,"image":332,"category":63,"interests":333,"order":335,"_id":336},"\u002Fmembers\u002Fstaff\u002Fying-weng","Ying Weng","assets\u002Fyingweng.png",[207,263,334],"IoT",4,"content:members:staff:ying-weng.md",{"_path":330,"title":87,"name":338,"role":88,"interests":339,"_id":342},"翁莹",[213,269,340,341],"物联网 IoT","无线网络安全与服务质量","content:members:staff:ying-weng.zh-CN.md",{"_path":344,"title":189,"name":345,"role":79,"email":26,"image":346,"category":63,"interests":347,"order":349,"_id":350},"\u002Fmembers\u002Fstaff\u002Fyuan-yao","Yuan Yao","assets\u002Fyuanyao.png",[348],"Autonomous Agents and Multi-Agent Systems",18,"content:members:staff:yuan-yao.md",{"_path":344,"title":197,"name":352,"role":88,"interests":353,"_id":355},"姚远",[354],"自主智能体与多智能体系统","content:members:staff:yuan-yao.zh-CN.md",{"_path":357,"title":189,"name":358,"role":110,"email":26,"image":359,"category":63,"interests":360,"order":362,"_id":363},"\u002Fmembers\u002Fstaff\u002Fzheng-lu","Zheng Lu","assets\u002F13.png",[361],"Computer Science",6,"content:members:staff:zheng-lu.md",{"_path":357,"title":197,"name":365,"role":119,"interests":366,"_id":368},"卢正",[367],"计算机科学","content:members:staff:zheng-lu.zh-CN.md",1782639517458]