# Refining Decompiled C Code with Large Language Models

> The paper proposes a two-step hybrid LLM approach to refine IDA-Pro decompiled C code for recompilation. On popular C test cases, it reports a recompilation success rate above 75% with moderate effort.

- Authors: Wai Kin Wong; Huaijin Wang; Zongjie Li; Zhibo Liu; Shuai Wang; Qiyi Tang; Sen Nie; Shi Wu
- Venue: arXiv
- Status: Preprint
- Publication / posting date: October 10, 2023
- Date source: First arXiv submission date.
- First arXiv submission: October 10, 2023
- arXiv: 2310.06530
- Reviewed arXiv version: v2
- Sources reviewed: 2026-11-06
- Added to the catalog: 2026-11-06
- Original paper: <https://arxiv.org/abs/2310.06530>
- PDF: <https://arxiv.org/pdf/2310.06530>
- BibTeX: <https://awesomerea.org/papers/citations/paper-dec-gpt.bib>
- Catalog page: <https://awesomerea.org/papers/paper-dec-gpt/>
- Record JSON: <https://awesomerea.org/papers/paper-dec-gpt/record.json>
- Chinese version: [简体中文](https://awesomerea.org/zh/papers/paper-dec-gpt/index.md)

## Scope and limitations

The pilot study examines obstacles in recompiling IDA-Pro output; the evaluation uses a set of popular C test cases.

## Why it fits this collection

It addresses reverse engineering of executables by improving decompiled C code for recompilation.

## Publication and review notes

The date and venue come from the arXiv record.

## Primary sources

1. <https://arxiv.org/abs/2310.06530>

## About this entry

Reviewed against the paper and its primary sources. Cite the original authors using the linked paper or BibTeX.
Original editorial content: MIT. Linked projects, papers and assets retain their own rights and licenses.