6 papers
Refactoring Programs Using Large Language Models with Few-Shot Examples
Atsushi Shirafuji, Yusuke Oda, Jun Suzuki +2
A less complex and more straightforward program is a crucial factor that enhances its maintainability and makes writing secure and bug-free programs easier. However, due to its hea…
Rule-Based Error Classification for Analyzing Differences in Frequent Errors
Atsushi Shirafuji, Taku Matsumoto, Md Faizul Ibne Amin +1
Finding and fixing errors is a time-consuming task not only for novice programmers but also for expert programmers. Prior work has identified frequent error patterns among various…
Program Repair with Minimal Edits Using CodeT5
Atsushi Shirafuji, Md. Mostafizer Rahman, Md Faizul Ibne Amin +1
Programmers often struggle to identify and fix bugs in their programs. In recent years, many language models (LMs) have been proposed to fix erroneous programs and support error re…
Exploring Automated Code Evaluation Systems and Resources for Code Analysis: A Comprehensive Survey
Md. Mostafizer Rahman, Yutaka Watanobe, Atsushi Shirafuji +1
The automated code evaluation system (AES) is mainly designed to reliably assess user-submitted code. Due to their extensive range of applications and the accumulation of valuable…
Deduplicating and Ranking Solution Programs for Suggesting Reference Solutions
Atsushi Shirafuji, Yutaka Watanobe
Referring to solution programs written by other users is helpful for learners in programming education. However, current online judge systems just list all solution programs submit…
Exploring the Robustness of Large Language Models for Solving Programming Problems
Atsushi Shirafuji, Yutaka Watanobe, Takumi Ito +4
Using large language models (LLMs) for source code has recently gained attention. LLMs, such as Transformer-based models like Codex and ChatGPT, have been shown to be highly capabl…