A study on prompt design, advantages and limitations of chatgpt for deep learning program repair

J Cao, M Li, M Wen, S Cheung - arXiv preprint arXiv:2304.08191, 2023 - arxiv.org
ChatGPT has revolutionized many research and industrial fields. ChatGPT has shown great
potential in software engineering to boost various traditional tasks such as program repair …

Repairing dnn architecture: Are we there yet?

J Kim, N Humbatova, G Jahangirova… - … IEEE Conference on …, 2023 - ieeexplore.ieee.org
As Deep Neural Networks (DNNs) are rapidly being adopted within large software systems,
software developers are increasingly required to design, train, and deploy such models into …

Personalized dialogue generation with persona-adaptive attention

Q Huang, Y Zhang, T Ko, X Liu, B Wu… - Proceedings of the …, 2023 - ojs.aaai.org
Persona-based dialogue systems aim to generate consistent responses based on historical
context and predefined persona. Unlike conventional dialogue generation, the persona …

ROME: Testing Image Captioning Systems via Recursive Object Melting

B Yu, Z Zhong, J Li, Y Yang, S He, P He - Proceedings of the 32nd ACM …, 2023 - dl.acm.org
Image captioning (IC) systems aim to generate a text description of the salient objects in an
image. In recent years, IC systems have been increasingly integrated into our daily lives …

Design by Contract for Deep Learning APIs

S Ahmed, SM Imtiaz, SS Khairunnesa… - Proceedings of the 31st …, 2023 - dl.acm.org
Deep Learning (DL) techniques are increasingly being incorporated in critical software
systems today. DL software is buggy too. Recent work in SE has characterized these bugs …

Adaptive search-based repair of deep neural networks

D Li Calsi, M Duran, T Laurent, XY Zhang… - Proceedings of the …, 2023 - dl.acm.org
Deep Neural Networks (DNNs) are finding a place at the heart of more and more critical
systems, and it is necessary to ensure they perform in as correct a way as possible. Search …

When debugging encounters artificial intelligence: state of the art and open challenges

Y Song, X Xie, B Xu - Science China Information Sciences, 2024 - Springer
Both software debugging and artificial intelligence techniques are hot topics in the current
field of software engineering. Debugging techniques, which comprise fault localization and …

Repairs and Breaks Prediction for Deep Neural Networks

Y Ishimoto, M Kondo, L Ma, N Ubayashi… - ACM Transactions on …, 2024 - dl.acm.org
With the increasing prevalence of software incorporating deep neural networks (DNNs),
quality assurance for these software systems has become a crucial concern. To this end …

Distributed repair of deep neural networks

DL Calsi, M Duran, XY Zhang, P Arcaini… - … IEEE Conference on …, 2023 - ieeexplore.ieee.org
Deep Neural Networks (DNNs) are applied in several safety-critical domains and their
trustworthiness is of paramount importance. For example, DNNs used in autonomous driving …

A two-stage framework for ambiguous classification in software engineering

J Li, Y Lei, S Li, H Zhou, Y Yu, Z Jia… - 2023 IEEE 34th …, 2023 - ieeexplore.ieee.org
Classification tasks are prevalent and play a crucial role in the field of software engineering.
However, when two classes exhibit similar features at the class level, the classification …