# Exploring Code Style Transfer with Neural Networks

arXiv: https://arxiv.org/abs/2209.06273 · HTML: https://mlsanity.com/paper/2209.06273/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 18 references that are in the map.
- First posted on arXiv 13 Sep 2022.

## Builds on (most cited first, 9 of 9)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation](https://mlsanity.com/paper/2109.00859/) (2021)
- [CodeBLEU: a Method for Automatic Evaluation of Code Synthesis](https://mlsanity.com/paper/2009.10297/) (2020)
- [Unified Pre-training for Program Understanding and Generation](https://mlsanity.com/paper/2103.06333/) (2021)
- [Deep Learning for Text Style Transfer: A Survey](https://mlsanity.com/paper/2011.00416/) (2020)
- [A Recipe For Arbitrary Text Style Transfer with Large Language Models](https://mlsanity.com/paper/2109.03910/) (2021)
- [Code Translation with Compiler Representations](https://mlsanity.com/paper/2207.03578/) (2022)
- [Style Transfer for Texts: Retrain, Report Errors, Compare with Rewrites](https://mlsanity.com/paper/1908.06809/) (2019)

## Built on by (most cited first, 2 of 2)

- [Poison with Style: A Practical Poisoning Attack on Code Large Language Models](https://mlsanity.com/paper/2605.27631/) (2026)
- [Excision Score: Evaluating Edits with Surgical Precision](https://mlsanity.com/paper/2510.21537/) (2025)

## Abstract (arXiv)

Style is a significant component of natural language text, reflecting a change in the tone of text while keeping the underlying information the same. Even though programming languages have strict syntax rules, they also have style. Code can be written with the same functionality but using different language features. However, programming style is difficult to quantify, and thus as part of this work, we define style attributes, specifically for Python. To build a definition of style, we utilized hierarchical clustering to capture a style definition without needing to specify transformations. In addition to defining style, we explore the capability of a pre-trained code language model to capture information about code style. To do this, we fine-tuned pre-trained code-language models and evaluated their performance in code style transfer tasks.