ALT4Decompile: Inferring C-aligned Abstract Loop Tree for LLM-Based Binary Decompilation

[2509.14646] ALT4Decompile: Inferring C-aligned Abstract Loop Tree for LLM-Based Binary Decompilation Skip to main content Search Submit Donate Log in Computer Science > Software Engineering arXiv:2509.14646 (cs) [Submitted on 18 Sep 2025 ( v1 ), last revised 25 Aug 2026 (this version, v2)] Title: ALT4Decompile: Inferring C-aligned Abstract Loop Tree for LLM-Based Binary Decompilation Authors: Yongpan Wang , Puzhuo Liu , Xin Xu , Siyuan Li , Yaowen zheng , Xiaodong Gu , Beijun Shen View PDF HTML (experimental) Abstract: Decompilation refers to the process of recovering high-level (C) language code from low-level (assembly) code. Recent Large Language Model (LLM)-based methods can generate re-executable code but struggle with the enormous syntax gap between assembly and C languages. Loop structures in C are fragmented into complex jumps within assembly languages, which poses a challenge to LLMs decompiling assembly language, which is mainly pre-trained on C. To bridge this gap, we propose ALT4Decompile, which refactors assembly to closely resemble C language structure, thereby preventing hallucinations in LLMs caused by complex jumps. Specifically, we construct a C-aligned \underline{\textbf{A}}bstract \underline{\textbf{L}}oop \underline{\textbf{T}}ree (ALT) based on specific jump patterns of Assembly that explicitly aggregates fragmented Assembly blocks into corresponding high-level loop structures (e.g., nested loops). Finally, we fine-tune an LLM adapted to ALT to generate decompiled code and then improve its output by fixing specific errors and restoring symbols. Evaluated against 12 baselines (including rule-based SAILR and LLM-based LLM4Decompile) on Decompile-Eval, MBPP, and ExeBench, ALT4Decompile achieves state-of-the-art correct re-executable results (even under four commonly used obfuscation techniques): i.e., a 70.4\% test case pass rate on Decompile-Eval, a 10.6\% improvement over prior best work. Furthermore, analyses on real-world software and a user study further show its practicability in understanding binary functions. The datasets and source code used in this paper are available at this https URL . Comments: 13 pages, 6 figures Subjects: Software Engineering (cs.SE) ; Programming Languages (cs.PL) Cite as: arXiv:2509.14646 [cs.SE] (or arXiv:2509.14646v2 [cs.SE] for this version) https://doi.org/10.48550/arXiv.2509.14646 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Yongpan Wang [ view email ] [v1] Thu, 18 Sep 2025 05:57:15 UTC (2,040 KB) [v2] Tue, 25 Aug 2026 07:58:48 UTC (2,327 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Current browse context: cs.SE < prev | next > new | recent | 2025-09 Change to browse by: cs cs.PL References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• ALT4Decompile: Inferring C-aligned Abstract Loop Tree for LLM-Based Binary Decompilation#670381
• VeriPilot: An LLM-Powered Verilog Debugging Framework#303297
• SDLLMFuzz: Dynamic-static LLM-assisted greybox fuzzing for structured input programs#120427
• Unfolding the Leech Lattice: Fused Multi-Shell Decoding and VRAM Layouts for 2-Bit LLM Weights#632844
• mold: A Massively Parallel Linker#1043171