Leveraging Large Language Models in Code Question Answering: Baselines and Issues

TL;DR

This paper explores fine-tuning large language models for Python code question answering, analyzing various data preprocessing techniques and highlighting dataset quality issues affecting performance.

Contribution

It introduces a fine-tuning approach for LLMs on Python code QA datasets and evaluates the impact of data preprocessing methods on answer quality.

Findings

Grammar correction improves testing metrics.

Public datasets have poor quality affecting results.

Manual error analysis reveals common answer errors.

Abstract

Question answering over source code provides software engineers and project managers with helpful information about the implemented features of a software product. This paper presents a work devoted to using large language models for question answering over source code in Python. The proposed method for implementing a source code question answering system involves fine-tuning a large language model on a unified dataset of questions and answers for Python code. To achieve the highest quality answers, we tested various models trained on datasets preprocessed in different ways: a dataset without grammar correction, a dataset with grammar correction, and a dataset augmented with the generated summaries. The model answers were also analyzed for errors manually. We report BLEU-4, BERTScore F1, BLEURT, and Exact Match metric values, along with the conclusions from the manual error analysis. The obtained experimental results highlight the current problems of the research area, such as poor quality of the public genuine question-answering datasets. In addition, the findings include the positive effect of the grammar correction of the training data on the testing metric values. The addressed findings and issues could be important for other researchers who attempt to improve the quality of source code question answering solutions. The training and evaluation code is publicly available at https://github.com/IU-AES-AI4Code/CodeQuestionAnswering.