D-LiFT: Improving LLM-based Decompiler Backend via Code Quality-driven Fine-tuning

• URL: http://arxiv.org/abs/2506.10125v1
• Date: Wed, 11 Jun 2025 19:09:08 GMT
• Title: D-LiFT: Improving LLM-based Decompiler Backend via Code Quality-driven Fine-tuning
• Authors: Muqi Zou, Hongyu Cai, Hongwei Wu, Zion Leonahenahe Basque, Arslan Khan, Berkay Celik, Dave, Tian, Antonio Bianchi, Ruoyu, Wang, Dongyan Xu,
• Abstract summary: We present D-LiFT, an automated decompiler backend that harnesses and trains LLMs to improve the quality of decompiled code via reinforcement learning (RL)<n>D-LiFT adheres to a key principle for enhancing the quality of decompiled code: textitpreserving accuracy while improving readability.<n>Central to D-LiFT, we propose D-SCORE, an integrated quality assessment system to score the decompiled code from multiple aspects.
• Score: 49.16469288280772
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Decompilers, which reconstruct human-readable source code from binary executables, are vital to many security tasks. Yet, despite recent advances, their output often suffers from syntactic and semantic errors and remains difficult to read. Recently, with the advent of large language models (LLMs), researchers began to explore the potential of LLMs to refine decompiler output. Nevertheless, our study of these approaches reveals significant limitations, such as introducing new errors and relying on unreliable accuracy validation. In this paper, we present D-LiFT, an automated decompiler backend that harnesses and further trains LLMs to improve the quality of decompiled code via reinforcement learning (RL). Unlike prior work that overlooks preserving accuracy, D-LiFT adheres to a key principle for enhancing the quality of decompiled code: \textit{preserving accuracy while improving readability}. Central to D-LiFT, we propose D-SCORE, an integrated quality assessment system to score the decompiled code from multiple aspects. In line with our principle, D-SCORE assigns low scores to any inaccurate output and only awards higher scores for readability to code that passes the accuracy check. Specifically, D-SCORE first verifies the syntactic and semantic correctness via the compiler and symbolic execution; only if a candidate is deemed accurate, it then evaluates readability using established metrics to compare the LLM output with the original decompiled code. The score will then be fed back to the LLM for fine-tuning. Our implementation, based on Ghidra and a range of LLMs, demonstrates significant improvements for the accurate decompiled code from the coreutils and util-linux projects. Compared to baseline LLMs without D-SCORE-driven fine-tuning, D-LiFT produces 55.3% more improved decompiled functions, as measured by D-SCORE.

Related papers

• IFEvalCode: Controlled Code Generation [69.28317223249358]
  The paper introduces forward and backward constraints generation to improve the instruction-following capabilities of Code LLMs.<n>The authors present IFEvalCode, a multilingual benchmark comprising 1.6K test samples across seven programming languages.
  arXiv  Detail & Related papers  (2025-07-30T08:08:48Z)
• Augmenting Large Language Models with Static Code Analysis for Automated Code Quality Improvements [0.36832029288386137]
  This study examined code issue detection and revision automation by integrating Large Language Models (LLMs) into software development.<n>A static code analysis framework detects issues such as bugs, vulnerabilities, and code smells within a large-scale software project.<n>Retrieval-augmented generation (RAG) is implemented to enhance the relevance and precision of the revisions.
  arXiv  Detail & Related papers  (2025-06-12T03:39:25Z)
• IterPref: Focal Preference Learning for Code Generation via Iterative Debugging [28.020886216989872]
  We propose IterPref, a new preference alignment framework for Code LLMs.<n>IterPref explicitly locates error regions and aligns the corresponding tokens via a tailored DPO algorithm.<n>IterPref achieves significant performance gains in code generation and improves on challenging tasks like BigCodeBench.
  arXiv  Detail & Related papers  (2025-03-04T16:56:34Z)
• ExeCoder: Empowering Large Language Models with Executability Representation for Code Translation [37.34003516231121]
  Code translation is a crucial activity in the software development and maintenance process.<n>Existing large language models (LLMs) only learn the contextual semantics of code during pre-training.<n>We propose ExeCoder, an LLM specifically designed for code translation.
  arXiv  Detail & Related papers  (2025-01-30T16:18:52Z)
• DSTC: Direct Preference Learning with Only Self-Generated Tests and Code to Improve Code LMs [56.4979142807426]
  We introduce underlinetextbfDirect Preference Learning with Only underlinetextbfSelf-Generated underlinetextbfTests and underlinetextbfCode (DSTC)<n>DSTC uses only self-generated code snippets and tests to construct reliable preference pairs.
  arXiv  Detail & Related papers  (2024-11-20T02:03:16Z)
• Utilizing Precise and Complete Code Context to Guide LLM in Automatic False Positive Mitigation [2.787944528438214]
  Static Application Security Testing (SAST) tools are critical to software quality, identifying potential code issues early in development.<n>They often produce false positive warnings that require manual review, slowing down development.<n>We propose LLM4FPM, a lightweight and efficient false positive mitigation framework.
  arXiv  Detail & Related papers  (2024-11-05T13:24:56Z)
• Improving LLM Reasoning through Scaling Inference Computation with Collaborative Verification [52.095460362197336]
  Large language models (LLMs) struggle with consistent and accurate reasoning. LLMs are trained primarily on correct solutions, reducing their ability to detect and learn from errors. We propose a novel collaborative method integrating Chain-of-Thought (CoT) and Program-of-Thought (PoT) solutions for verification.
  arXiv  Detail & Related papers  (2024-10-05T05:21:48Z)
• InverseCoder: Self-improving Instruction-Tuned Code LLMs with Inverse-Instruct [43.7550233177368]
  This paper explores whether it is possible to use a fine-tuned open-source model to generate additional data to augment its instruction-tuning dataset.<n>We propose Inverse-Instruct, a data augmentation technique that uses a fine-tuned LLM to generate additional instructions of code responses from its own training dataset.
  arXiv  Detail & Related papers  (2024-07-08T08:00:05Z)
• Bug In the Code Stack: Can LLMs Find Bugs in Large Python Code Stacks [1.3586572110652484]
  This study explores the capabilities of Large Language Models (LLMs) in retrieving contextual information from large text documents. Our benchmark, Bug In The Code Stack (BICS), is designed to assess the ability of LLMs to identify simple syntax bugs within large source code. Our findings reveal three key insights: (1) code-based environments pose significantly more challenge compared to text-based environments for retrieval tasks, (2) there is a substantial performance disparity among different models, and (3) there is a notable correlation between longer context lengths and performance degradation.
  arXiv  Detail & Related papers  (2024-06-21T17:37:10Z)
• Uncovering LLM-Generated Code: A Zero-Shot Synthetic Code Detector via Code Rewriting [78.48355455324688]
  We propose a novel zero-shot synthetic code detector based on the similarity between the original code and its LLM-rewritten variants.<n>Our results demonstrate a significant improvement over existing SOTA synthetic content detectors.
  arXiv  Detail & Related papers  (2024-05-25T08:57:28Z)
• LLM4Decompile: Decompiling Binary Code with Large Language Models [10.346311290153398]
  Decompilation aims to convert binary code to high-level source code, but traditional tools like Ghidra often produce results difficult to read and execute. We propose LLM4Decompile, the first and largest open-source LLM series (1.3B to 33B) trained to decompile binary code. The resulting models significantly outperform GPT-4o and Ghidra on the HumanEval and ExeBench benchmarks by over 100% in terms of re-executability rate.
  arXiv  Detail & Related papers  (2024-03-08T13:10:59Z)
• StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback [58.20547418182074]
  We introduce StepCoder, a novel framework for code generation, consisting of two main components. CCCS addresses the exploration challenge by breaking the long sequences code generation task into a Curriculum of Code Completion Subtasks. FGO only optimize the model by masking the unexecuted code segments to provide Fine-Grained Optimization. Our method improves the ability to explore the output space and outperforms state-of-the-art approaches in corresponding benchmarks.
  arXiv  Detail & Related papers  (2024-02-02T13:14:31Z)
• Fixing Large Language Models' Specification Misunderstanding for Better Code Generation [13.494822086550604]
  muFiX is a novel prompting technique to improve the code generation performance of large language models (LLMs)<n>It first exploits test case analysis to obtain specification understanding and enables a self-improvement process.<n>muFiX further fixes the specification understanding towards the direction reducing the gap between the provided understanding and the actual understanding.
  arXiv  Detail & Related papers  (2023-09-28T02:58:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.