Towards LLM-Generated Code Tours for Onboarding

Research output: Contribution in Book/Catalog/Report/Conference proceedingConference contribution

7 Downloads (Pure)

Abstract

Onboarding new developers is a challenge for any software project. Addressing this challenge relies on human resources (e.g., having a senior developer write documentation or mentor the new developer). One promising solution is using annotated code tours. While this approach partially lifts the need for mentorship, it still requires a senior developer to write this interactive form of documentation. This paper argues that a Large Language Model (LLM) might help with this documentation process. Our approach is to record the stack trace between a failed test and a faulty method. We then extract code snippets from the methods in this stack trace using CodeQL, a static analysis tool and have them explained by gpt-3.5-turbo-1106, the LLM behind ChatGPT. Finally, we evaluate the quality of a sample of these generated tours using a checklist. We show that the automatic generation of code tours is feasible but has limitations like redundant and low-level explanations.
Original languageEnglish
Title of host publication2024 ACM/IEEE International Workshop on NL-based Software Engineering (NLBSE ’24)
Place of PublicationLisbon, Portugal
PublisherACM Press
DOIs
Publication statusPublished - Apr 2024
Event3rd Intl. Workshop on NL-based Software Engineering - Lisbon, Portugal
Duration: 20 Apr 202420 Apr 2024
Conference number: 3
https://nlbse2024.github.io

Conference

Conference3rd Intl. Workshop on NL-based Software Engineering
Abbreviated titleNLBSE '24
Country/TerritoryPortugal
CityLisbon
Period20/04/2420/04/24
Internet address

Fingerprint

Dive into the research topics of 'Towards LLM-Generated Code Tours for Onboarding'. Together they form a unique fingerprint.

Cite this