arXiv · 2610.06900
ASAP: Assembly-Source Aligned Pseudocode Refinement For Binary Decompilation
Abstract
Large language models (LLMs) are increasingly used in binary decompilation to refine the C-like pseudocode produced by traditional rule-based decompilers. While this pseudocode is useful, it is a heuristic and lossy abstraction rather than a faithful copy of the source code. It often contains decompiler errors, especially for aggressively optimized binaries where critical low-level details are obscured. We present ASAP, an Assembly-Source Aligned Pseudocode refinement framework for binary decompilation. ASAP learns source-aligned assembly representations from paired source and binary functions using joint function-level and snippet-level contrastive alignment. A Q-Former then compresses chunk-level assembly features into a fixed number of assembly tokens. These tokens and the decompiler-produced pseudocode jointly condition the decompilation LLM. During refinement, we use stochastic pseudocode masking and a relative assembly-advantage loss to discourage the model from relying solely on pseudocode. On two decompilation benchmarks across multiple compiler optimization levels, ASAP improves the average re-execution rate from 64.7% to 71.9% and the average recompilation rate from 91.6% to 96.6% compared with the strongest baseline. Our approach offers both a new perspective and a practical solution to binary decompilation.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Yujian Zhuang, Dehong Gao, Qichao Zhang, Qijing Lai, Jiaxin Wang, Libin Yang, Xiaoyan Cai. 2026-11-12. ASAP: Assembly-Source Aligned Pseudocode Refinement For Binary Decompilation. https://searcharxiv.com/abs/2610.06900
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.