Leveraging GPT-like LLMs to Automate Issue Labeling

Issue labeling is a crucial task for the effective management of software projects. To date, several approaches have been put forth for the automatic assignment of labels to issue reports. In particular, supervised approaches based on the fine-tuning of BERT-like language models have been proposed,...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings (IEEE/ACM International Conference on Mining Software Repositories. Online) s. 469 - 480
Hlavní autoři: Colavito, Giuseppe, Lanubile, Filippo, Novielli, Nicole, Quaranta, Luigi
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: ACM 15.04.2024
Témata:
Annotations
Computational modeling
Data models
GPT
Issue Labeling
Labeling Unstructured Data
LLM
Manuals
Scalability
Software
Software Maintenance and Evolution
Supervised learning
ISSN:2574-3864
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Issue labeling is a crucial task for the effective management of software projects. To date, several approaches have been put forth for the automatic assignment of labels to issue reports. In particular, supervised approaches based on the fine-tuning of BERT-like language models have been proposed, achieving state-of-the-art performance. More recently, decoder-only models such as GPT have become prominent in SE research due to their surprising capabilities to achieve state-of-the-art performance even for tasks they have not been trained for. To the best of our knowledge, GPT-like models have not been applied yet to the problem of issue classification, despite the promising results achieved for many other software engineering tasks. In this paper, we investigate to what extent we can leverage GPT-like LLMs to automate the issue labeling task. Our results demonstrate the ability of GPT-like models to correctly classify issue reports in the absence of labeled data that would be required to fine-tune BERT-like LLMs.CCS CONCEPTS* Software and its engineering → Documentation; Software evolution; Maintaining software; * Information systems → Clustering and classification;
ISSN:2574-3864
DOI:10.1145/3643991.3644903