# LLM4Decompile: Decompiling Binary Code with Large Language Models

> Trains language models for assembly-to-C decompilation and for refining Ghidra pseudocode, evaluating whether recovered functions can be recompiled and executed correctly.

- Authors: Hanzhuo Tan; Qi Luo; Jing Li; Yuqun Zhang
- Venue: EMNLP 2024
- Status: Conference paper
- Publication / posting date: November 2024
- Date source: ACL proceedings publication month
- First arXiv submission: March 8, 2024
- arXiv: 2403.05286
- Reviewed arXiv version: v3
- DOI: 10.18653/v1/2024.emnlp-main.203
- Sources reviewed: 2026-10-16
- Added to the catalog: 2026-10-16
- Original paper: <https://aclanthology.org/2024.emnlp-main.203/>
- PDF: <https://aclanthology.org/2024.emnlp-main.203.pdf>
- Code: <https://github.com/albertan017/LLM4Decompile>
- BibTeX: <https://awesomerea.org/papers/citations/paper-llm4decompile.bib>
- Catalog page: <https://awesomerea.org/papers/paper-llm4decompile/>
- Record JSON: <https://awesomerea.org/papers/paper-llm4decompile/record.json>
- Chinese version: [简体中文](https://awesomerea.org/zh/papers/paper-llm4decompile/index.md)

## Scope and limitations

The paper limits its experiments to C on x86 and function-level benchmarks. Re-executability on sampled tests does not establish whole-program equivalence or recovery of the original source. Later repository releases are separate from the 2024 paper.

## Why it fits this collection

Direct evidence for LLM decompilation and a concrete baseline for evaluating agent-generated or refined pseudocode.

## Publication and review notes

Publication date is the conference month; the first arXiv submission date is listed separately.

## Primary sources

1. <https://aclanthology.org/2024.emnlp-main.203/>
2. <https://aclanthology.org/2024.emnlp-main.203.pdf>
3. <https://arxiv.org/abs/2403.05286>
4. <https://github.com/albertan017/LLM4Decompile>
5. <https://github.com/albertan017/LLM4Decompile/blob/85b364bf093eb2ee4f3687cfe38a203fca89f23e/README.md>

## Related entries

- [LLM4Decompile (EMNLP 2024)](https://awesomerea.org/resources/llm4decompile-paper/index.md) · Curated resource

## 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.