Self-Constructed Context Decompilation with Fined-grained Alignment Enhancement

TL;DR

This paper introduces a novel decompilation approach combining self-constructed context and fine-grained alignment, significantly improving performance by 3.9% and setting new state-of-the-art results.

Contribution

It proposes two innovative methods, sc$^2$dec and FAE, to enhance decompilation accuracy without extensive fine-tuning or large-scale data.

Findings

Achieved 52.41% re-executability on Decompile-Eval benchmark.

Improved decompilation performance by approximately 3.90%.

Established new state-of-the-art results.

Abstract

Decompilation transforms compiled code back into a high-level programming language for analysis when source code is unavailable. Previous work has primarily focused on enhancing decompilation performance by increasing the scale of model parameters or training data for pre-training. Based on the characteristics of the decompilation task, we propose two methods: (1) Without fine-tuning, the Self-Constructed Context Decompilation (sc$^2$dec) method recompiles the LLM's decompilation results to construct pairs for in-context learning, helping the model improve decompilation performance. (2) Fine-grained Alignment Enhancement (FAE), which meticulously aligns assembly code with source code at the statement level by leveraging debugging information, is employed during the fine-tuning phase to achieve further improvements in decompilation. By integrating these two methods, we achieved a Re-Executability performance improvement of approximately 3.90% on the Decompile-Eval benchmark, establishing a new state-of-the-art performance of 52.41%. The code, data, and models are available at https://github.com/AlongWY/sccdec.