--- title: "LLM4Decompile" type: "tool" slug: "albertan017-llm4decompile" canonical_url: "https://www.graphcanon.com/tools/albertan017-llm4decompile" github_url: "https://github.com/albertan017/LLM4Decompile" homepage_url: "https://aclanthology.org/2024.emnlp-main.203" stars: 6741 forks: 536 primary_language: "Python" license: "MIT" categories: ["model-training", "llm-frameworks"] tags: ["binary", "decompile", "large-language-models", "reverse-engineering"] updated_at: "2026-07-07T18:37:39.595208+00:00" --- # LLM4Decompile > Reverse Engineering: Decompiling Binary Code with Large Language Models Repository for reverse engineering binary code using large language models, including tools and models for decompilation. ## Facts - Repository: https://github.com/albertan017/LLM4Decompile - Homepage: https://aclanthology.org/2024.emnlp-main.203 - Stars: 6,741 · Forks: 536 · Open issues: 46 · Watchers: 75 - Primary language: Python - License: MIT - Last pushed: 2026-02-12T03:02:03+00:00 ## Categories - [Model Training](/categories/model-training.md) - [LLM Frameworks](/categories/llm-frameworks.md) ## Tags binary, decompile, large language models, reverse-engineering ## Related tools - [ollama](/tools/ollama-ollama.md) - Get up and running with Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models. (★ 175,659) - [prompts.chat](/tools/f-prompts-chat.md) - The world's largest open-source prompt library for AI (★ 165,019) - [transformers](/tools/huggingface-transformers.md) - 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models (★ 162,347) - [open-webui](/tools/open-webui-open-webui.md) - User-friendly AI Interface (Supports Ollama, OpenAI API, ...) (★ 144,575) - [awesome-llm-apps](/tools/shubhamsaboo-awesome-llm-apps.md) - 100+ AI Agent & RAG apps you can actually run — clone, customize, ship. (★ 116,702) - [LLMs-from-scratch](/tools/rasbt-llms-from-scratch.md) - Implement a ChatGPT-like LLM in PyTorch from scratch (★ 98,711) - [TradingAgents](/tools/tauricresearch-tradingagents.md) - TradingAgents: Multi-Agents LLM Financial Trading Framework (★ 91,610) - [caveman](/tools/juliusbrussee-caveman.md) - Cuts 65% of tokens in AI coding agent responses. (★ 86,150) ## README (excerpt) ```text

LLM4Decompile

📊 Results | 🤗 Models | 🚀 Quick Start | 📚 HumanEval-Decompile | 📎 Citation | 📝 Paper | 🖥️ Colab | ▶️ YouTube

Reverse Engineering: Decompiling Binary Code with Large Language Models ## Updates * [2025-10-04]: Release SK²Decompile: LLM-based Two-Phase Binary Decompilation from Skeleton to Skin. Phase 1 Structure Recovery (Skeleton): Transform binary/pseudo-code into obfuscated intermediate representations 🤗 [HF Link](https://huggingface.co/LLM4Binary/sk2decompile-struct-6.7b). Phase 2 Identifier Naming (Skin): Generate human-readable source code with meaningful identifiers 🤗 [HF Link](https://huggingface.co/LLM4Binary/sk2decompile-ident-6.7). * [2025-05-20]: Release [decompile-bench](https://huggingface.co/collections/LLM4Binary/decompile-bench-68259091c8d49d0ebd5efda9), contains two million binary-source function pairs for training, and 70K function pairs for evaluation. Please refer to the [decompile-bench](https://github.com/albertan017/LLM4Decompile/tree/main/decompile-bench) folder for details. * [2024-10-17]: Release [decompile-ghidra-100k](https://huggingface.co/datasets/LLM4Binary/decompile-ghidra-100k), a subset of 100k training samples (25k per optimization level). We provide a [training script](https://github.com/albertan017/LLM4Decompile/blob/main/train/README.md) that runs in ~3.5 hours on a single A100 40G GPU. It achieves a 0.26 re-executability rate, with a total cost of under $20 for quick replication of LLM4Decompile. * [2024-09-26]: Update a [Colab notebook](https://colab.research.google.com/drive/1X5TuUKuNuksGJZz6Cc83KKI0ATBP9q7r?usp=sharing) to demonstrate the usage of the LLM4Decompile model, including examples for the LLM4Decompile-End and LLM4Decompile-Ref models. * [2024-09-23]: Release [LLM4Decompile-9B-v2](https://huggingface.co/LLM4Binary/llm4decompile-9b-v2), fine-tuned based on [Yi-Coder-9B](https://huggingface.co/01-ai/Yi-Coder-9B), achieved a re-executability rate of **0.6494** on the Decompile benchmark. * [2024-06-19]: Release [V2](https://huggingface.co/LLM4Binary/llm4decompile-6.7b-v2) series (LLM4Decompile-Ref). V2 (1.3B-22B), building upon **Ghidra**, are trained on 2 billion tokens to **refine** the decompiled pseudo-code from Ghidra. The 22B-V2 version outperforms the 6.7B-V1.5 by an additional 40.1%. Please check the [ghidra folder](https://github.com/albertan017/LLM4Decompile/tree/main/ghidra) for details. * [2024-05-13]: Release [V1.5](https://huggingface.co/LLM4Binary/llm4decompile-6.7b-v1.5) series (LLM4Decompile-End, directly decompile binary using LLM). V1.5 are trained with a larger dataset (15B tokens) and a maximum token **length of 4,096**, with remarkable performance (over **100% improvement**) compared to the previous model. * [2024-03-16]: Add [llm4decompile-6.7b-uo](https://huggingface.co/arise-sustech/llm4decompile-6.7b-uo) model which is trained without prior knowledge of the optimization levels (O0~O3), the average re-executability is around 0.219, performs the best in our models. ## About * **LLM4Decompile** is the pioneering open-source large language model dedicated to decompilation. Its current version supports decompiling Linux x86_64 binaries, ranging from GCC's O0 to O3 optimization levels, into human-readable C source cod ``` --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/tools/albertan017-llm4decompile`](/api/graphcanon/tools/albertan017-llm4decompile) - LLM index: [/llms.txt](/llms.txt) - Full corpus: [/llms-full.txt](/llms-full.txt) _GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_