EUVIMEDEUVIMED entdecken
Crossref

Distilled GPT for source code summarization

Chia-Yi Su, Collin McMillan

Automated Software Engineering · 2024-05 · 31 (1)

DOI: 10.1007/s10515-024-00421-4 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Automated Software Engineering, online erschienen am 01.03.2024. Verfasst von Chia-Yi Su und 1 weiteren Autor:innen. Die Arbeit wurde bisher 56-mal zitiert (Crossref) und nennt 72 Literaturangaben. Gefördert von: National Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A code summary is a brief natural language description of source code. Summaries are usually only a single sentence long, and yet form the backbone of developer documentation. A short descriptions such as “changes all visible polygons to the color blue” can give a programmer a high-level idea of what code does without the effort of reading the code itself. Recently, products based on Large Language Models such as ChatGPT have demonstrated a strong ability to write these descriptions automatically. However, to use these tools, programmers must send their code to untrusted third parties for processing (e.g., via an API call). This loss of custody is not acceptable to many organizations. In this paper, we present an alternative: we train an open source model using sample output generated by GPT $$-$$ - 3.5 in a process related to knowledge distillation. Our model is small enough (350 m parameters) to be run on a single 16gb GPU, yet we show in our evaluation that it is large enough to mimic GPT $$-$$ - 3.5 on this task.

Förderung

  • National Science Foundation

Zitieren

APA

Su, C., & McMillan, C. (2024). Distilled GPT for source code summarization. Automated Software Engineering, 31(1). https://doi.org/10.1007/s10515-024-00421-4

Vancouver

Su C, McMillan C. Distilled GPT for source code summarization. Automated Software Engineering. 2024;31(1). doi:10.1007/s10515-024-00421-4

BibTeX
@article{Su2024,
  author = {Su, Chia-Yi and McMillan, Collin},
  title = {Distilled GPT for source code summarization},
  journal = {Automated Software Engineering},
  year = {2024},
  volume = {31},
  number = {1},
  doi = {10.1007/s10515-024-00421-4}
}
Kostenlos starten →