# Fast, Fine-Grained Equivalence Checking for Neural Decompilers

arXiv: https://arxiv.org/abs/2501.04811 · HTML: https://mlsanity.com/paper/2501.04811/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 53 references that are in the map.
- First posted on arXiv 8 Jan 2025.

## Builds on (most cited first, 11 of 11)

- [CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation](https://mlsanity.com/paper/2109.00859/) (2021)
- [CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation](https://mlsanity.com/paper/2102.04664/) (2021)
- [CodeBLEU: a Method for Automatic Evaluation of Code Synthesis](https://mlsanity.com/paper/2009.10297/) (2020)
- [CodeT5+: Open Code Large Language Models for Code Understanding and Generation](https://mlsanity.com/paper/2305.07922/) (2023)
- [CodeBERTScore: Evaluating Code Generation with Pretrained Models of Code](https://mlsanity.com/paper/2302.05527/) (2023)
- [TBar: Revisiting Template-based Automated Program Repair](https://mlsanity.com/paper/1903.08409/) (2019)
- [Does BLEU Score Work for Code Migration?](https://mlsanity.com/paper/1906.04903/) (2019)
- [DIRE: A Neural Approach to Decompiled Identifier Naming](https://mlsanity.com/paper/1909.09029/) (2019)
- [SLaDe: A Portable Small Language Model Decompiler for Optimized Assembly](https://mlsanity.com/paper/2305.12520/) (2023)
- [Augmenting Decompiler Output with Learned Variable Names and Types](https://mlsanity.com/paper/2108.06363/) (2021)
- [Boosting Neural Networks to Decompile Optimized Binaries](https://mlsanity.com/paper/2301.00969/) (2023)

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

- [LOOPRAG: Enhancing Loop Transformation Optimization with Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2512.15766/) (2025)
- [Recompilation Is Not Enough: Test-Guided Decompiled-C Repair](https://mlsanity.com/paper/2609.07201/) (2026)

## Abstract (arXiv)

Neural decompilers are machine learning models that reconstruct the source code from an executable program. Critical to the lifecycle of any machine learning model is an evaluation of its effectiveness. However, existing techniques for evaluating neural decompilation models have substantial weaknesses, especially when it comes to showing the correctness of the neural decompiler's predictions. To address this, we introduce codealign, a novel instruction-level code equivalence technique designed for neural decompilers. We provide a formal definition of a relation between equivalent instructions, which we term an equivalence alignment. We show how codealign generates equivalence alignments, then evaluate codealign by comparing it with symbolic execution. Finally, we show how the information codealign provides-which parts of the functions are equivalent and how well the variable names match-is substantially more detailed than existing state-of-the-art evaluation metrics, which report unitless numbers measuring similarity.