Please use this identifier to cite or link to this item:
http://bura.brunel.ac.uk/handle/2438/29885
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Destefanis, G | - |
dc.contributor.author | Bartolucci, S | - |
dc.contributor.author | Ortu, M | - |
dc.date.accessioned | 2024-10-06T10:06:23Z | - |
dc.date.available | 2024-10-06T10:06:23Z | - |
dc.date.issued | 2023-05-16 | - |
dc.identifier | ORCiD: Giuseppe Destefanis https://orcid.org/0000-0003-3982-6355 | - |
dc.identifier | arXiv:2305.09402v1 [cs.SE] | - |
dc.identifier.citation | Destefanis, G., Bartolucci, S. and Ortu, M. (2023) 'A Preliminary Analysis on the Code Generation Capabilities of GPT-3.5 and Bard AI Models for Java Functions', arXiv:2305.09402v1 [cs.SE], pp. 1 - 11. doi: 10.48550/arXiv.2305.09402. | en_US |
dc.identifier.uri | https://bura.brunel.ac.uk/handle/2438/29885 | - |
dc.description | The preprint version archived on this insttutional repository is available online at: https://arxiv.org/abs/2305.09402 . It has not been certified by peer review. | en_US |
dc.description.abstract | This paper evaluates the capability of two state-of-the-art artificial intelligence (AI) models, GPT-3.5 and Bard, in generating Java code given a function description. We sourced the descriptions from CodingBat.com, a popular online platform that provides practice problems to learn programming. We compared the Java code generated by both models based on correctness, verified through the platform's own test cases. The results indicate clear differences in the capabilities of the two models. GPT-3.5 demonstrated superior performance, generating correct code for approximately 90.6% of the function descriptions, whereas Bard produced correct code for 53.1% of the functions. While both models exhibited strengths and weaknesses, these findings suggest potential avenues for the development and refinement of more advanced AI-assisted code generation tools. The study underlines the potential of AI in automating and supporting aspects of software development, although further research is required to fully realize this potential. | en_US |
dc.format.extent | 1 - 11 | - |
dc.format.medium | Electronic | - |
dc.language.iso | en_US | en_US |
dc.publisher | Cornell University | en_US |
dc.rights | Attribution 4.0 International | - |
dc.rights.uri | https://creativecommons.org/licenses/by/4.0/ | - |
dc.subject | software engineering (cs.SE) | en_US |
dc.subject | computation and language (cs.CL) | en_US |
dc.title | A Preliminary Analysis on the Code Generation Capabilities of GPT-3.5 and Bard AI Models for Java Functions | en_US |
dc.type | Article | en_US |
dc.identifier.doi | https://doi.org/10.48550/arXiv.2305.09402 | - |
dc.identifier.eissn | 2331-8422 | - |
dc.rights.license | https://creativecommons.org/licenses/by/4.0/legalcode.en | - |
dc.rights.holder | The Authors | - |
Appears in Collections: | Dept of Computer Science Research Papers |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Preprint.pdf | Copyright © 2023 The Author(s). This work is licensed under a Creative Commons Attribution 4.0 International License (https://creativecommons.org/licenses/by/4.0/). | 354.65 kB | Adobe PDF | View/Open |
This item is licensed under a Creative Commons License