ChatGPT for Code Refactoring: Analyzing Topics, Interaction, and Effective Prompts
Bibliographic record
Abstract
Large Language Models (LLMs), such as ChatGPT, have become widely popular and widely used in various software engineering tasks such as refactoring, testing, code review, and program comprehension. Although recent studies have examined the effectiveness of LLMs in recommending and suggesting refactoring, there is a limited understanding of how developers express their refactoring needs when interacting with ChatGPT. In this paper, our goal is to explore interactions related to refactoring between developers and ChatGPT to better understand how developers identify areas for improvement in code, and how ChatGPT addresses developers' needs. Our approach involves text mining 715 refactoring-related interactions from 29,778 ChatGPT prompts and responses, as well as the analysis of developers' explicit refactoring intentions. Our results reveal that (1) refactoring interactions between developers and ChatGPT encompass 25 themes including 'Quality', 'Objective', 'Testing', and 'Design', (2) ChatGPT's use of affirmation phrases such as 'certainly' regarding refactoring decisions, and apology phrases such as 'apologize' when resolving refactoring challenges, and (3) our refactoring prompt template enables developers to obtain concise, accurate, and satisfactory responses with minimal interactions. We envision our results enhancing researchers and practitioners understanding of how developers interact with LLMs during code refactoring.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.010 | 0.091 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.004 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".