Search Results for author:
Found 5 papers, 0 papers with code
Refactoring Programs Using Large Language Models with Few-Shot Examples
A less complex and more straightforward program is a crucial factor that enhances its maintainability and makes writing secure and bug-free programs easier.
Rule-Based Error Classification for Analyzing Differences in Frequent Errors
We classify errors for 95, 631 code pairs and identify 3. 47 errors on average, which are submitted by various levels of programmers on an online judge system.
Program Repair with Minimal Edits Using CodeT5
The experimental results show that the fine-tuned CodeT5 achieves a pass@100 of 91. 95% and an average edit distance of the most similar correct program of 6. 84, which indicates that at least one correct program can be suggested by generating 100 candidate programs.
Deduplicating and Ranking Solution Programs for Suggesting Reference Solutions
The proposed approach shows the potential of reducing the learners' burden of referring to too many solutions and motivating them to learn a variety of solution approaches.
Exploring the Robustness of Large Language Models for Solving Programming Problems
Our experimental results show that CodeGen and Codex are sensitive to the superficial modifications of problem descriptions and significantly impact code generation performance.
