LLaMA-Reviewer: Advancing Code Review Automation with Large Language Models through Parameter-Efficient Fine-Tuning

The automation of code review activities, a long-standing pursuit in software engineering, has been primarily addressed by numerous domain-specific pre-trained models. Despite their success, these models frequently demand extensive resources for pre-training from scratch. In contrast, Large Language...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Proceedings - International Symposium on Software Reliability Engineering s. 647 - 658
Hlavní autori: Lu, Junyi, Yu, Lei, Li, Xiaojia, Yang, Li, Zuo, Chun
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 09.10.2023
Predmet:
Automation
Code Review Automation
Codes
Deep Learning
Large Language Models (LLMs)
LLaMA
Parameter-Efficient Fine-Tuning (PEFT)
Quality assurance
Software engineering
Software Quality Assurance
Software reliability
Task analysis
Tuning
ISSN:2332-6549
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:The automation of code review activities, a long-standing pursuit in software engineering, has been primarily addressed by numerous domain-specific pre-trained models. Despite their success, these models frequently demand extensive resources for pre-training from scratch. In contrast, Large Language Models (LLMs) provide an intriguing alternative, given their remarkable capabilities when supplemented with domain-specific knowledge. However, their potential for automating code review tasks remains largely unexplored.In response to this research gap, we present LLaMA-Reviewer, an innovative framework that leverages the capabilities of LLaMA, a popular LLM, in the realm of code review. Mindful of resource constraints, this framework employs parameter-efficient fine-tuning (PEFT) methods, delivering high performance while using less than 1% of trainable parameters.An extensive evaluation of LLaMA-Reviewer is conducted on two diverse, publicly available datasets. Notably, even with the smallest LLaMA base model consisting of 6.7B parameters and a limited number of tuning epochs, LLaMA-Reviewer equals the performance of existing code-review-focused models.The ablation experiments provide insights into the influence of various fine-tuning process components, including input representation, instruction tuning, and different PEFT methods. To foster continuous progress in this field, the code and all PEFT-weight plugins have been made open-source.
ISSN:2332-6549
DOI:10.1109/ISSRE59848.2023.00026