Improving Web Element Localization by Using a Large Language Model

Michel Nass, Emil Alégroth, ROBERT H. FELDT

Software Testing Verification and Reliability 2024 article cited by 16

importance 3/10 ai assisted Software Testing and Debugging Techniques software testing stage: research proprietary model

Web-based test automation requires accurately locating web elements, but traditional attribute-matching methods miss context and meaning of elements and words.

Element localization accuracy directly determines the reliability of automated web testing.

VON Similo LLM uses a large language model to select the most likely web element from top-ranked candidates produced by the existing VON Similo method, evaluated on 804 element pairs from 48 real-world web applications.

Correctly identified elements and execution times were measured on 804 pairs from 48 apps; values not stated in source

Peer-reviewed experimental study of LLM-based element selection; improvement magnitude not verifiable from abstract.

Venue Software Testing Verification and Reliability
Published 2024
Work type article
Authors Michel Nass, Emil Alégroth, ROBERT H. FELDT
Citations 16 (OpenAlex, at import time)
References 53
Model or method VON Similo LLM (LLM-based; GPT-4 cited as context)
Organization not stated in source
Primary source https://doi.org/10.1002/stvr.1893
Open access hybrid
Keywords web element localization, LLM, test automation, GPT-4, software testing
3 / 10

incremental / niche

Element localization accuracy affects reliability of automated web testing and maintenance costs; a genuine but niche software engineering improvement.

Basis: inferred. Judged from the source text, which gives no explicit scale. Stated scale: not stated in source. Method and limits.

# Paper Year Citations Importance
1 ImageNet classification with deep convolutional neural networks
Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton
2017 106,345
8
2 Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun
2016 221,134
8
3 Faster sorting algorithms discovered using deep reinforcement learning
Daniel J. Mankowitz, Andrea Michi, Anton Zhernov, Marco Gelmi, Marco S...
2023 175
8
4 A deep learning‐based approach for software vulnerability detection using code metrics
Fazli Subhan, Xiaoxue Wu, Lili Bo, Xiaobing Sun, Muhammad Rahman
2022 42
7
5 Deep Learning-Based Attack Detection and Classification in Android Devices
Alfonso Gómez, Antonio Muñoz
2023 41
7