Finetuning LLMs for Automatic Form Interaction on Web-Browser in Selenium Testing Framework
This addresses a specific bottleneck in web application testing for software developers, though it appears incremental as it applies existing LLM techniques to a new domain.
The paper tackles the problem of generating automated test cases for web form interaction using large language models, introducing a method that outperforms GPT-4o and other LLMs across syntax correctness, executability, and coverage metrics.
Automated web application testing is a critical component of modern software development, with frameworks like Selenium widely adopted for validating functionality through browser automation. Among the essential aspects of such testing is the ability to interact with and validate web forms, a task that requires syntactically correct, executable scripts with high coverage of input fields. Despite its importance, this task remains underexplored in the context of large language models (LLMs), and no public benchmark or dataset exists to evaluate LLMs on form interaction generation systematically. This paper introduces a novel method for training LLMs to generate high-quality test cases in Selenium, specifically targeting form interaction testing. We curate both synthetic and human-annotated datasets for training and evaluation, covering diverse real-world forms and testing scenarios. We define clear metrics for syntax correctness, script executability, and input field coverage. Our empirical study demonstrates that our approach significantly outperforms strong baselines, including GPT-4o and other popular LLMs, across all evaluation metrics. Our work lays the groundwork for future research on LLM-based web testing and provides resources to support ongoing progress in this area.