FRANC: A Lightweight Framework for High-Quality Code Generation
This program is tentative and subject to change.
In recent years, the use of automated source code generation utilizing transformer-based generative models has expanded, and these models can generate functional code according to the developers’ requirements. However, recent research revealed 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 time-consuming, resource-intensive and costly. Thus, in this manuscript, 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.
This program is tentative and subject to change.
Tue 8 OctDisplayed time zone: Mountain Time (US & Canada) change
10:30 - 12:00 | |||
10:30 22mTalk | AUTOGENICS: Automated Generation of Context-Aware Inline Comments for Code Snippets on Programming Q&A Sites Using LLM Research Track Suborno Deb Bappon Department of Computer Science, University of Saskatchewan, Canada, Saikat Mondal University of Saskatchewan, Banani Roy University of Saskatchewan Pre-print | ||
10:52 22mTalk | Code Search Oriented Node-Enhanced Control Flow Graph Embedding Research Track | ||
11:15 22mResearch paper | FRANC: A Lightweight Framework for High-Quality Code Generation Research Track Mohammed Latif Siddiq University of Notre Dame, Beatrice Casey University of Notre Dame, Joanna C. S. Santos University of Notre Dame Pre-print | ||
11:37 22mTalk | REINFOREST: Reinforcing Semantic Code Similarity for Cross-Lingual Code Search Models Research Track Pre-print |