aalto1 untyped-item.component.html

Evaluating the readability of code generated by large language models

Loading...
Thumbnail Image

Files

URL

Journal Title

Journal ISSN

Volume Title

Perustieteiden korkeakoulu | Bachelor's thesis
Electronic archive copy is available locally at the Harald Herlin Learning Centre. The staff of Aalto University has access to the electronic bachelor's theses by logging into Aaltodoc with their personal Aalto user ID. Read more about the availability of the bachelor's theses.

Department

Major/Subject

Mcode

SCI3095

Language

en

Pages

25

Series

Abstract

The recent development of large language models (LLMs) and artificial intelligence (AI) has stimulated the emergence of various AI-powered tools for programming. As developers and companies have started to utilize such tools in software development, numerous concerns have been raised regarding their ability to assist developers and improve efficiency. This thesis focuses on code readability and its evaluation in the context of AI-generated code, providing a summary of the current research in this area. The literature review shows that studies on this topic typically involve code generation using various methods, including solving programming challenges, experimenting with human developers, and utilizing search queries. Following code generation, the readability evaluation is conducted through one or more approaches including human assessment, readability models, and metric-based analyses. The results indicate that LLMs and AI demonstrate commendable performance in generating code with good readability. However, it is important to note the inherent limitations of each evaluation method, and readability alone does not guarantee that the generated code is immediately usable. This thesis further addresses the limitations of readability evaluation and additional concerns regarding AI-generated code.

Description

Supervisor

Korpi-Lagg, Maarit

Thesis advisor

Ahrenberg, Lukas

Other note

Citation

Endorsement

Review

Supplemented By

Referenced By