UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Enhancing Genetic Improvement Mutations Using Large Language Models

Brownlee, Alexander EI; Callan, James; Even-Mendoza, Karine; Geiger, Alina; Hanna, Carol; Petke, Justyna; Sarro, Federica; (2023) Enhancing Genetic Improvement Mutations Using Large Language Models. In: SSBSE 2023: Search-Based Software Engineering. 15th International Symposium. Springer Green open access

[thumbnail of main.pdf]
Preview
Text
main.pdf - Accepted Version

Download (194kB) | Preview

Abstract

Large language models (LLMs) have been successfully applied to software engineering tasks, including program repair. However, their application in search-based techniques such as Genetic Improvement (GI) is still largely unexplored. In this paper, we evaluate the use of LLMs as mutation operators for GI to improve the search process. We expand the Gin Java GI toolkit to call OpenAI’s API to generate edits for the JCodec tool. We randomly sample the space of edits using 5 different edit types. We find that the number of patches passing unit tests is up to 75% higher with LLM-based edits than with standard Insert edits. Further, we observe that the patches found with LLMs are generally less diverse compared to standard edits. We ran GI with local search to find runtime improvements. Although many improving patches are found by LLM-enhanced GI, the best improving patch was found by standard GI.

Type: Proceedings paper
Title: Enhancing Genetic Improvement Mutations Using Large Language Models
Event: SSBSE 2023: Search-Based Software Engineering. 15th International Symposium
Open access status: An open access version is available from UCL Discovery
DOI: 10.1007/978-3-031-48796-5_13
Publisher version: https://doi.org/10.1007/978-3-031-48796-5_13
Language: English
Additional information: This version is the author accepted manuscript. - For the purpose of open access, the author has applied a Creative Commons Attribution (CC BY) licence to any Author Accepted Manuscript version arising.
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI: https://discovery.ucl.ac.uk/id/eprint/10180563
Downloads since deposit
9Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item