# FidelityGPT: Correcting Decompilation Distortions with Retrieval Augmented Generation

arXiv: https://arxiv.org/abs/2510.19615 · HTML: https://mlsanity.com/paper/2510.19615/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in RAG for code, one of 15 directions in Retrieval-augmented generation.
- Builds on 19 of its 53 references that are in the map.
- First posted on arXiv 22 Oct 2025.

## Placed in

- Retrieval-augmented generation / [RAG for code](https://mlsanity.com/rag/rag-for-code/)

## Builds on (most cited first, 19 of 19)

- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2405.06211/) (2024)
- [Retrieval-Augmented Generation for AI-Generated Content: A Survey](https://mlsanity.com/paper/2402.19473/) (2024)
- [Do Prompt-Based Models Really Understand the Meaning of their Prompts?](https://mlsanity.com/paper/2109.01247/) (2021)
- [RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models](https://mlsanity.com/paper/2401.00396/) (2023)
- [The Power of Noise: Redefining Retrieval for RAG Systems](https://mlsanity.com/paper/2401.14887/) (2024)
- [The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)](https://mlsanity.com/paper/2402.16893/) (2024)
- [DRAGIN: Dynamic Retrieval Augmented Generation based on the Information Needs of Large Language Models](https://mlsanity.com/paper/2403.10081/) (2024)
- [HITS: High-coverage LLM-based Unit Test Generation via Method Slicing](https://mlsanity.com/paper/2408.11324/) (2024)
- [A study on Prompt Design, Advantages and Limitations of ChatGPT for Deep Learning Program Repair](https://mlsanity.com/paper/2304.08191/) (2023)
- [An Observational Investigation of Reverse Engineers' Processes](https://mlsanity.com/paper/1912.00317/) (2019)
- [LongHeads: Multi-Head Attention is Secretly a Long Context Processor](https://mlsanity.com/paper/2402.10685/) (2024)
- [DomainRAG: A Chinese Benchmark for Evaluating Domain-specific Retrieval-Augmented Generation](https://mlsanity.com/paper/2406.05654/) (2024)
- [CP-BCS: Binary Code Summarization Guided by Control Flow Graph and Pseudo Code](https://mlsanity.com/paper/2310.16853/) (2023)
- [FT2Ra: A Fine-Tuning-Inspired Approach to Retrieval-Augmented Code Completion](https://mlsanity.com/paper/2404.01554/) (2024)
- [SV-TrustEval-C: Evaluating Structure and Semantic Reasoning in Large Language Models for Source Code Vulnerability Analysis](https://mlsanity.com/paper/2505.20630/) (2025)
- [Variable Name Recovery in Decompiled Binary Code using Constrained Masked Language Modeling](https://mlsanity.com/paper/2103.12801/) (2021)
- [Automatically Mitigating Vulnerabilities in Binary Programs via Partially Recompilable Decompilation](https://mlsanity.com/paper/2202.12336/) (2022)
- [VulCatch: Enhancing Binary Vulnerability Detection through CodeT5 Decompilation and KAN Advanced Feature Extraction](https://mlsanity.com/paper/2408.07181/) (2024)

## Built on by (most cited first, 2 of 2)

- [PCodeTrans: Translate Decompiled Pseudocode to Compilable and Executable Equivalent](https://mlsanity.com/paper/2603.14855/) (2026)
- [Beyond Text Matching: Towards Reference-Free Evaluation for Human-Oriented Binary Reverse Engineering](https://mlsanity.com/paper/2608.07038/) (2026)

## Abstract (arXiv)

Decompilation converts machine code into human-readable form, enabling analysis and debugging without source code. However, fidelity issues often degrade the readability and semantic accuracy of decompiled output. Existing methods, such as variable renaming or structural simplification, provide partial improvements but lack robust detection and correction, particularly for complex closed-source binaries. We present FidelityGPT, a framework that enhances decompiled code accuracy and readability by systematically detecting and correcting semantic distortions. FidelityGPT introduces distortion-aware prompt templates tailored to closed-source settings and integrates Retrieval-Augmented Generation (RAG) with a dynamic semantic intensity algorithm to locate distorted lines and retrieve semantically similar code from a database. A variable dependency algorithm further mitigates long-context limitations by analyzing redundant variables and integrating their dependencies into the prompt context. Evaluated on 620 function pairs from a binary similarity benchmark, FidelityGPT achieved an average detection accuracy of 89% and a precision of 83%. Compared to the state-of-the-art DeGPT (Fix Rate 83%, Corrected Fix Rate 37%), FidelityGPT attained 94% FR and 64% CFR, demonstrating significant gains in accuracy and readability. These results highlight its potential to advance LLM-based decompilation and reverse engineering.