# Code Translation with Compiler Representations

arXiv: https://arxiv.org/abs/2207.03578 · HTML: https://mlsanity.com/paper/2207.03578/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 43 references that are in the map.
- First posted on arXiv 30 Jun 2022.

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [Cross-lingual Language Model Pretraining](https://mlsanity.com/paper/1901.07291/) (2019)
- [CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation](https://mlsanity.com/paper/2109.00859/) (2021)
- [Improving Neural Machine Translation Models with Monolingual Data](https://mlsanity.com/paper/1511.06709/) (2015)
- [GraphCodeBERT: Pre-training Code Representations with Data Flow](https://mlsanity.com/paper/2009.08366/) (2020)
- [Unified Pre-training for Program Understanding and Generation](https://mlsanity.com/paper/2103.06333/) (2021)
- [Unsupervised Machine Translation Using Monolingual Corpora Only](https://mlsanity.com/paper/1711.00043/) (2017)
- [Unsupervised Translation of Programming Languages](https://mlsanity.com/paper/2006.03511/) (2020)
- [SPoC: Search-based Pseudocode to Code](https://mlsanity.com/paper/1906.04908/) (2019)
- [Phrase-Based & Neural Unsupervised Machine Translation](https://mlsanity.com/paper/1804.07755/) (2018)
- [Tree-to-tree Neural Networks for Program Translation](https://mlsanity.com/paper/1802.03691/) (2018)
- [Leveraging Automated Unit Tests for Unsupervised Code Translation](https://mlsanity.com/paper/2110.06773/) (2021)
- [DOBF: A Deobfuscation Pre-Training Objective for Programming Languages](https://mlsanity.com/paper/2102.07492/) (2021)
- [Unsupervised Statistical Machine Translation](https://mlsanity.com/paper/1809.01272/) (2018)
- [Perfection Not Required? Human-AI Partnerships in Code Translation](https://mlsanity.com/paper/2104.03820/) (2021)
- [Towards Neural Decompilation](https://mlsanity.com/paper/1905.08325/) (2019)
- [Better Together? An Evaluation of AI-Supported Code Translation](https://mlsanity.com/paper/2202.07682/) (2022)
- [Semantics-Recovering Decompilation through Neural Machine Translation](https://mlsanity.com/paper/2112.15491/) (2021)

## Built on by (most cited first, 30 of 42)

- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [Multi-lingual Evaluation of Code Generation Models](https://mlsanity.com/paper/2210.14868/) (2022)
- [SWE-PolyBench: A multi-language benchmark for repository level evaluation of coding agents](https://mlsanity.com/paper/2504.08703/) (2025)
- [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)
- [RepoTransBench: A Real-World Multilingual Benchmark for Repository-Level Code Translation](https://mlsanity.com/paper/2412.17744/) (2024)
- [CodeRosetta: Pushing the Boundaries of Unsupervised Code Translation for Parallel Programming](https://mlsanity.com/paper/2410.20527/) (2024)
- [EMMA-500: Enhancing Massively Multilingual Adaptation of Large Language Models](https://mlsanity.com/paper/2409.17892/) (2024)
- [InterTrans: Leveraging Transitive Intermediate Translations to Enhance LLM-based Code Translation](https://mlsanity.com/paper/2411.01063/) (2024)
- [Scope is all you need: Transforming LLMs for HPC Code](https://mlsanity.com/paper/2308.09440/) (2023)
- [MonoCoder: Domain-Specific Code Language Model for HPC Codes and Tasks](https://mlsanity.com/paper/2312.13322/) (2023)
- [Rethinking Multilingual Continual Pretraining: Data Mixing for Adapting LLMs Across Languages and Resources](https://mlsanity.com/paper/2504.04152/) (2025)
- [Coeditor: Leveraging Contextual Changes for Multi-round Code Auto-editing](https://mlsanity.com/paper/2305.18584/) (2023)
- [Compiler generated feedback for Large Language Models](https://mlsanity.com/paper/2403.14714/) (2024)
- [SACTOR: LLM-Driven Correct and Idiomatic C to Rust Translation with Static Analysis and FFI-Based Verification](https://mlsanity.com/paper/2503.12511/) (2025)
- [GALLa: Graph Aligned Large Language Models for Improved Source Code Understanding](https://mlsanity.com/paper/2409.04183/) (2024)
- [TransAgent: Enhancing LLM-Based Code Translation via Fine-Grained Execution Alignment](https://mlsanity.com/paper/2409.19894/) (2024)
- [CASCADE: LLM-Powered JavaScript Deobfuscator at Google](https://mlsanity.com/paper/2507.17691/) (2025)
- [Fortran2CPP: Automating Fortran-to-C++ Translation using LLMs via Multi-Turn Dialogue and Dual-Agent Integration](https://mlsanity.com/paper/2412.19770/) (2024)
- [ObscuraCoder: Powering Efficient Code LM Pre-Training Via Obfuscation Grounding](https://mlsanity.com/paper/2504.00019/) (2025)
- [Massively Multilingual Adaptation of Large Language Models Using Bilingual Translation Data](https://mlsanity.com/paper/2506.00469/) (2025)
- [Function-to-Style Guidance of LLMs for Code Translation](https://mlsanity.com/paper/2507.11083/) (2025)
- [Automatically Testing Functional Properties of Code Translation Models](https://mlsanity.com/paper/2309.12813/) (2023)
- [Guess & Sketch: Language Model Guided Transpilation](https://mlsanity.com/paper/2309.14396/) (2023)
- [Mastering the Craft of Data Synthesis for CodeLLMs](https://mlsanity.com/paper/2411.00005/) (2024)
- [Renaissance of Literate Programming in the Era of LLMs: Enhancing LLM-Based Code Generation in Large-Scale Projects](https://mlsanity.com/paper/2502.17441/) (2024)
- [Post-Incorporating Code Structural Knowledge into Pretrained Models via ICL for Code Translation](https://mlsanity.com/paper/2503.22776/) (2025)
- [Exploring Code Style Transfer with Neural Networks](https://mlsanity.com/paper/2209.06273/) (2022)
- [Forklift: An Extensible Neural Lifter](https://mlsanity.com/paper/2404.16041/) (2024)

## Abstract (arXiv)

In this paper, we leverage low-level compiler intermediate representations (IR) to improve code translation. Traditional transpilers rely on syntactic information and handcrafted rules, which limits their applicability and produces unnatural-looking code. Applying neural machine translation (NMT) approaches to code has successfully broadened the set of programs on which one can get a natural-looking translation. However, they treat the code as sequences of text tokens, and still do not differentiate well enough between similar pieces of code which have different semantics in different languages. The consequence is low quality translation, reducing the practicality of NMT, and stressing the need for an approach significantly increasing its accuracy. Here we propose to augment code translation with IRs, specifically LLVM IR, with results on the C++, Java, Rust, and Go languages. Our method improves upon the state of the art for unsupervised code translation, increasing the number of correct translations by 11% on average, and up to 79% for the Java -> Rust pair with greedy decoding. We extend previous test sets for code translation, by adding hundreds of Go and Rust functions. Additionally, we train models with high performance on the problem of IR decompilation, generating programming source code from IR, and study using IRs as intermediary pivot for translation.