EditLord: Learning Code Transformation Rules for Code Editing

Weichen Li, Albert Jan, Baishakhi Ray, Junfeng Yang, Chengzhi Mao, Kexin Pei

Keywords: Large Language Models, Machine Learning for Code Editing, Code Generation, Reasoning

TL;DR: The paper introduces EditLord, a novel framework that enhances LLMs for code editing by introducing discrete and explicit procedural steps, leading to improved performance on various code editing tasks and better robustness.

Track: Long Paper (up to 9 pages)

Abstract:

Code editing is a foundational task in software development, where its effectiveness depends on whether it introduces desired code property changes without changing the original code's intended functionality.
Existing approaches often formulate code editing as an implicit end-to-end task, omitting the fact that code-editing procedures inherently consist of discrete and explicit steps, and thus suffer from suboptimal performance and lack of robustness and generalization.
We introduce EditLord, a code editing framework that makes the code transformation steps explicit.
Our key insight is to employ a language model (LM) as an inductive learner to extract code editing rules from the training code pairs as concise meta-rule sets.
Such rule sets will be manifested for each training sample to augment them for finetuning or assist in prompting- and iterative-based code editing.
EditLord outperforms the state-of-the-art by an average of 22.7% in editing performance and 58.1% in robustness while achieving 20.2% higher functional correctness, across critical software engineering and security applications, LM models, and editing modes.

Format: We have read the camera-ready instructions, and our paper is formatted with the provided template.

De-Anonymization: This submission has been de-anonymized.

Anonymization: This submission has been anonymized for double-blind review via the removal of identifying information such as names, affiliations, and identifying URLs.

Submission Number: 25