Franc: A Lightweight Framework for High-Quality Code Generation

In recent years, the use of automated source code generation utilizing transformer-based generative models has grown in popularity. These models can generate code according to the developers' requirements. However, recent research showed that these automatically generated source codes can contain vulnerabilities and other quality issues. Despite researchers' and practitioners' attempts to enhance code generation models, retraining and fine-tuning large language models is not only time-consuming but also resource-intensive and costly. Thus, in this paper, we describe FRANC, a lightweight framework for recommending more secure and high-quality source code derived from transformer-based code generation models. FRANC includes a static filter to make the generated code compilable with heuristics and a quality-aware ranker to sort the code snippets based on a quality score. Moreover, the framework uses prompt engineering to fix persistent quality issues. We evaluated FRANC with five Python and Java code generation models and six prompt datasets, including a newly created one in this work (FRANC). The static filter improves 9% to 46% Java suggestions and 10% to 43% Python suggestions regarding compilability. The average improvement over the NDCG@10 score for the ranking system is 0.0763, and the repairing techniques repair the highest 80% of prompts. FRANC takes, on average, 1.98 seconds for Java; for Python, it takes 0.08 seconds.

I. Introduction

Large Language Models (LLMs) are increasingly performing well in many natural language processing tasks, such as text generation, translation, and summarization [1]. One particularly relevant application of these LLMs to software engineering is code generation, in which LLMs are trained and fine-tuned with large amounts of code snippets [2]–[5]. These techniques help developers by generating the implementation of functions/programs based on provided prompts [6].