Résumé
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.CCS CONCEPTS• Computing methodologies → Natural language generation; • Software and its engineering → Software development process management.
langue originale | Anglais |
---|---|
titre | Proceedings - 2024 ACM/IEEE International Workshop on NL-Based Software Engineering, NLBSE 2024 |
Lieu de publication | Lisbon, Portugal |
Editeur | ACM Press |
Pages | 65-68 |
Nombre de pages | 4 |
ISBN (Electronique) | 9798400705762 |
Les DOIs | |
Etat de la publication | Publié - avr. 2024 |
Evénement | 3rd Intl. Workshop on NL-based Software Engineering - Lisbon, Portugal Durée: 20 avr. 2024 → 20 avr. 2024 Numéro de conférence: 3 https://nlbse2024.github.io |
Série de publications
Nom | Proceedings - 2024 ACM/IEEE International Workshop on NL-Based Software Engineering, NLBSE 2024 |
---|
Une conférence
Une conférence | 3rd Intl. Workshop on NL-based Software Engineering |
---|---|
Titre abrégé | NLBSE '24 |
Pays/Territoire | Portugal |
La ville | Lisbon |
période | 20/04/24 → 20/04/24 |
Adresse Internet |