# SLaDe: A Portable Small Language Model Decompiler for Optimized Assembly

arXiv: https://arxiv.org/abs/2305.12520 · HTML: https://mlsanity.com/paper/2305.12520/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 68 references that are in the map.
- First posted on arXiv 21 May 2023.

## Builds on (most cited first, 28 of 28)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [fairseq: A Fast, Extensible Toolkit for Sequence Modeling](https://mlsanity.com/paper/1904.01038/) (2019)
- [CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation](https://mlsanity.com/paper/2102.04664/) (2021)
- [Unsupervised Translation of Programming Languages](https://mlsanity.com/paper/2006.03511/) (2020)
- [Byte Pair Encoding is Suboptimal for Language Model Pretraining](https://mlsanity.com/paper/2004.03720/) (2020)
- [Tree-to-tree Neural Networks for Program Translation](https://mlsanity.com/paper/1802.03691/) (2018)
- [AVATAR: A Parallel Corpus for Java-Python Program Translation](https://mlsanity.com/paper/2108.11590/) (2021)
- [An Effective Approach to Unsupervised Machine Translation](https://mlsanity.com/paper/1902.01313/) (2019)
- [DIRE: A Neural Approach to Decompiled Identifier Naming](https://mlsanity.com/paper/1909.09029/) (2019)
- [Towards Neural Decompilation](https://mlsanity.com/paper/1905.08325/) (2019)
- [Beyond the C: Retargetable Decompilation using Neural Machine Translation](https://mlsanity.com/paper/2212.08950/) (2022)
- [Evaluating Transformer Language Models on Arithmetic Operations Using Number Decomposition](https://mlsanity.com/paper/2304.10977/) (2023)
- [Cross-Language Binary-Source Code Matching with Intermediate Representations](https://mlsanity.com/paper/2201.07420/) (2022)
- [Large Language Models Based Automatic Synthesis of Software Specifications](https://mlsanity.com/paper/2304.09181/) (2023)
- [Learning C to x86 Translation: An Experiment in Neural Compilation](https://mlsanity.com/paper/2108.07639/) (2021)
- [Boosting Neural Networks to Decompile Optimized Binaries](https://mlsanity.com/paper/2301.00969/) (2023)
- [Modeling Black-Box Components with Probabilistic Synthesis](https://mlsanity.com/paper/2010.04811/) (2020)
- [Datalog Disassembly](https://mlsanity.com/paper/1906.03969/) (2019)
- [Program Language Translation Using a Grammar-Driven Tree-to-Tree Model](https://mlsanity.com/paper/1807.01784/) (2018)

## Built on by (most cited first, 28 of 28)

- [Large Language Models for Cyber Security: A Systematic Literature Review](https://mlsanity.com/paper/2405.04760/) (2024)
- [Unifying the Perspectives of NLP and Software Engineering: A Survey on Language Models for Code](https://mlsanity.com/paper/2311.07989/) (2023)
- [Large Language Models for Compiler Optimization](https://mlsanity.com/paper/2309.07062/) (2023)
- [Meta Large Language Model Compiler: Foundation Models of Compiler Optimization](https://mlsanity.com/paper/2407.02524/) (2024)
- [Nova: Generative Language Models for Assembly Code with Hierarchical Attention and Contrastive Learning](https://mlsanity.com/paper/2311.13721/) (2023)
- [Don't Transform the Code, Code the Transforms: Towards Precise Code Rewriting using LLMs](https://mlsanity.com/paper/2410.08806/) (2024)
- [Identify Critical Nodes in Complex Network with Large Language Models](https://mlsanity.com/paper/2403.03962/) (2024)
- [VecTrans: Enhancing Compiler Auto-Vectorization through LLM-Assisted Code Transformations](https://mlsanity.com/paper/2503.19449/) (2025)
- [Guess & Sketch: Language Model Guided Transpilation](https://mlsanity.com/paper/2309.14396/) (2023)
- [HELIOS: Hierarchical Graph Abstraction for Structure-Aware LLM Decompilation](https://mlsanity.com/paper/2601.14598/) (2026)
- [Forklift: An Extensible Neural Lifter](https://mlsanity.com/paper/2404.16041/) (2024)
- [Fast, Fine-Grained Equivalence Checking for Neural Decompilers](https://mlsanity.com/paper/2501.04811/) (2025)
- [Small Language Models (SLMs) Can Still Pack a Punch: A survey (updated 2026)](https://mlsanity.com/paper/2501.05465/) (2025)
- [Towards LLM-based optimization compilers. Can LLMs learn how to apply a single peephole optimization? Reasoning is all LLMs need!](https://mlsanity.com/paper/2412.12163/) (2024)
- [Can Large Language Models Understand Intermediate Representations in Compilers?](https://mlsanity.com/paper/2502.06854/) (2025)
- [Context-Guided Decompilation: A Step Towards Re-executability](https://mlsanity.com/paper/2511.01763/) (2025)
- [Decaf: Improving Neural Decompilation with Automatic Feedback and Search](https://mlsanity.com/paper/2605.11501/) (2026)
- [AutoPass: Evidence-Guided LLM Agents for Compiler Performance Tuning](https://mlsanity.com/paper/2606.20373/) (2026)
- [Guaranteed Guess: A Language Modeling Approach for CISC-to-RISC Transpilation with Testing Guarantees](https://mlsanity.com/paper/2506.14606/) (2025)
- [Large Language Models in Cybersecurity: Applications, Vulnerabilities, and Defense Techniques](https://mlsanity.com/paper/2507.13629/) (2025)
- [QiMeng-NeuComBack: Self-Evolving Translation from IR to Assembly Code](https://mlsanity.com/paper/2511.01183/) (2025)
- [Exploring the Feasibility of End-to-End Large Language Model as a Compiler](https://mlsanity.com/paper/2511.04132/) (2025)
- [The New Compiler Stack: A Survey on the Synergy of LLMs and Compilers](https://mlsanity.com/paper/2601.02045/) (2026)
- [Decomposer: Learning to Decompile Symbolic Music to Programs](https://mlsanity.com/paper/2607.01849/) (2026)
- [Evaluating Neural Decompilation of Dart AOT Binaries: Fine-Tuning, Metric Validity, Specification Leakage, and Reliability](https://mlsanity.com/paper/2607.06125/) (2026)
- [Reveree: Diagnosing LLM Reverse-Engineering Agents](https://mlsanity.com/paper/2609.01185/) (2026)
- [When LLM Decompilers Recompile More and Preserve Less](https://mlsanity.com/paper/2609.05370/) (2026)
- [Echo: Learning-based Matching Decompilation using Trusted Back Translation](https://mlsanity.com/paper/2609.18706/) (2026)

## Abstract (arXiv)

Decompilation is a well-studied area with numerous high-quality tools available. These are frequently used for security tasks and to port legacy code. However, they regularly generate difficult-to-read programs and require a large amount of engineering effort to support new programming languages and ISAs. Recent interest in neural approaches has produced portable tools that generate readable code. However, to-date such techniques are usually restricted to synthetic programs without optimization, and no models have evaluated their portability. Furthermore, while the code generated may be more readable, it is usually incorrect. This paper presents SLaDe, a Small Language model Decompiler based on a sequence-to-sequence transformer trained over real-world code. We develop a novel tokenizer and exploit no-dropout training to produce high-quality code. We utilize type-inference to generate programs that are more readable and accurate than standard analytic and recent neural approaches. Unlike standard approaches, SLaDe can infer out-of-context types and unlike neural approaches, it generates correct code. We evaluate SLaDe on over 4,000 functions from ExeBench on two ISAs and at two optimizations levels. SLaDe is up to 6 times more accurate than Ghidra, a state-of-the-art, industrial-strength decompiler and up to 4 times more accurate than the large language model ChatGPT and generates significantly more readable code than both.