Refactoring to Pythonic Idioms: A Hybrid Knowledge-Driven Approach Leveraging Large Language Models

TL;DR

This paper introduces RIdiom, a hybrid knowledge-driven approach combining rules and large language models to accurately detect and refactor Python code into idiomatic forms, outperforming existing methods.

Contribution

It presents a novel hybrid framework integrating rule-based and LLM techniques for Pythonic idiom refactoring, addressing limitations of previous approaches.

Findings

RIdiom achieves over 90% accuracy and F1-score on nine established idioms.

The approach outperforms Prompt-LLM in all evaluated metrics.

It maintains high precision while significantly improving recall and F1-score.

Abstract

Pythonic idioms are highly valued and widely used in the Python programming community. However, many Python users find it challenging to use Pythonic idioms. Adopting a rule-based approach or LLM-only approach is not sufficient to overcome three persistent challenges of code idiomatization including code miss, wrong detection and wrong refactoring. Motivated by the determinism of rules and adaptability of LLMs, we propose a hybrid approach consisting of three modules. We not only write prompts to instruct LLMs to complete tasks, but we also invoke Analytic Rule Interfaces (ARIs) to accomplish tasks. The ARIs are Python code generated by prompting LLMs to generate code. We first construct a knowledge module with three elements including ASTscenario, ASTcomponent and Condition, and prompt LLMs to generate Python code for incorporation into an ARI library for subsequent use. After that, for any syntax-error-free Python code, we invoke ARIs from the ARI library to extract ASTcomponent from the ASTscenario, and then filter out ASTcomponent that does not meet the condition. Finally, we design prompts to instruct LLMs to abstract and idiomatize code, and then invoke ARIs from the ARI library to rewrite non-idiomatic code into the idiomatic code. Next, we conduct a comprehensive evaluation of our approach, RIdiom, and Prompt-LLM on nine established Pythonic idioms in RIdiom. Our approach exhibits superior accuracy, F1-score, and recall, while maintaining precision levels comparable to RIdiom, all of which consistently exceed or come close to 90% for each metric of each idiom. Lastly, we extend our evaluation to encompass four new Pythonic idioms. Our approach consistently outperforms Prompt-LLM, achieving metrics with values consistently exceeding 90% for accuracy, F1-score, precision, and recall.