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

• URL: http://arxiv.org/abs/2411.03012v1
• Date: Tue, 05 Nov 2024 11:25:12 GMT
• Title: Leveraging Large Language Models in Code Question Answering: Baselines and Issues
• Authors: Georgy Andryushchenko, Vladimir Ivanov, Vladimir Makharev, Elizaveta Tukhtina, Aidar Valeev,
• Abstract summary: 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. We report BLEU-4, BERTScore F1, BLEURT, and Exact Match metric values, along with the conclusions from the manual error analysis.
• Score: 0.1617522438111378
• License:
• 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.

Related papers

• Lean Workbook: A large-scale Lean problem set formalized from natural language math problems [50.22847430754973]
  Large language models are not good at math theorem proving using formal languages like Lean. A significant challenge in this area is the scarcity of training data available in these formal languages. We propose a novel pipeline that iteratively generates and filters synthetic data to translate natural language mathematical problems into Lean 4 statements.
  arXiv  Detail & Related papers  (2024-06-06T08:25:43Z)
• DataAgent: Evaluating Large Language Models' Ability to Answer Zero-Shot, Natural Language Queries [0.0]
  We evaluate OpenAI's GPT-3.5 as a "Language Data Scientist" (LDS) The model was tested on a diverse set of benchmark datasets to evaluate its performance across multiple standards.
  arXiv  Detail & Related papers  (2024-03-29T22:59:34Z)
• Enhancing Code Intelligence Tasks with ChatGPT [17.712126698173535]
  ChatGPT-generated comments demonstrate superior semantic consistency with the code compared to human references. We rebuild the widely used dataset, CodeSearchNet, with ChatGPT-generated comments. Results show that the model pre-trained by ChatGPT-enhanced data outperforms its counterpart on code summarization, code generation, and code translation tasks.
  arXiv  Detail & Related papers  (2023-12-23T09:01:08Z)
• Teaching Large Language Models to Self-Debug [62.424077000154945]
  Large language models (LLMs) have achieved impressive performance on code generation. We propose Self- Debugging, which teaches a large language model to debug its predicted program via few-shot demonstrations.
  arXiv  Detail & Related papers  (2023-04-11T10:43:43Z)
• Python Code Generation by Asking Clarification Questions [57.63906360576212]
  In this work, we introduce a novel and more realistic setup for this task. We hypothesize that the under-specification of a natural language description can be resolved by asking clarification questions. We collect and introduce a new dataset named CodeClarQA containing pairs of natural language descriptions and code with created synthetic clarification questions and answers.
  arXiv  Detail & Related papers  (2022-12-19T22:08:36Z)
• Improving Classifier Training Efficiency for Automatic Cyberbullying Detection with Feature Density [58.64907136562178]
  We study the effectiveness of Feature Density (FD) using different linguistically-backed feature preprocessing methods. We hypothesise that estimating dataset complexity allows for the reduction of the number of required experiments. The difference in linguistic complexity of datasets allows us to additionally discuss the efficacy of linguistically-backed word preprocessing.
  arXiv  Detail & Related papers  (2021-11-02T15:48:28Z)
• CodeQA: A Question Answering Dataset for Source Code Comprehension [82.63394952538292]
  Given a code snippet and a question, a textual answer is required to be generated. CodeQA contains a Java dataset with 119,778 question-answer pairs and a Python dataset with 70,085 question-answer pairs.
  arXiv  Detail & Related papers  (2021-09-17T06:06:38Z)
• Program Synthesis with Large Language Models [40.41120807053989]
  We evaluate large language models for program synthesis in Python. We find that synthesis performance scales log-linearly with model size. We find that even our best models are generally unable to predict the output of a program given a specific input.
  arXiv  Detail & Related papers  (2021-08-16T03:57:30Z)
• Break-It-Fix-It: Unsupervised Learning for Program Repair [90.55497679266442]
  We propose a new training approach, Break-It-Fix-It (BIFI), which has two key ideas. We use the critic to check a fixer's output on real bad inputs and add good (fixed) outputs to the training data. Based on these ideas, we iteratively update the breaker and the fixer while using them in conjunction to generate more paired data. BIFI outperforms existing methods, obtaining 90.5% repair accuracy on GitHub-Python and 71.7% on DeepFix.
  arXiv  Detail & Related papers  (2021-06-11T20:31:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.