Why Attention Fails: A Taxonomy of Faults in Attention-Based Neural Networks
Open Access
- 12 April 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 3053-3065
Abstract
No abstract availableAll Related Versions
This publication has 54 references indexed in Scilit:
- Characterizing and classifying developer forum posts with their intentionsEmpirical Software Engineering, 2024
- Bug characterization in machine learning-based systemsEmpirical Software Engineering, 2023
- Silent bugs in deep learning frameworks: an empirical study of Keras and TensorFlowEmpirical Software Engineering, 2023
- Insights into software development approaches: mining Q &A repositoriesEmpirical Software Engineering, 2023
- Bugs in machine learning-based systems: a faultload benchmarkEmpirical Software Engineering, 2023
- Attention mechanism in neural networks: where it comes and where it goesNeural Computing and Applications, 2022
- Attention, please! A survey of neural attention models in deep learningArtificial Intelligence Review, 2022
- Faults in deep reinforcement learning programs: a taxonomy and a detection approachAutomated Software Engineering, 2021
- How different are different diff algorithms in Git?Empirical Software Engineering, 2019
- A study of the stratified random samplingAnnals of the Institute of Statistical Mathematics, 1954