# Program Translation via Code Distillation

arXiv: https://arxiv.org/abs/2310.11476 · HTML: https://mlsanity.com/paper/2310.11476/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge and representations inside LLMs, one of 13 directions in Mechanistic interpretability.
- Builds on 17 of its 24 references that are in the map.
- First posted on arXiv 17 Oct 2023.

## Placed in

- Mechanistic interpretability / [Knowledge and representations inside LLMs](https://mlsanity.com/mechinterp/knowledge-and-representations-inside-llms/)

## Builds on (most cited first, 17 of 17)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [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)
- [CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation](https://mlsanity.com/paper/2102.04664/) (2021)
- [GraphCodeBERT: Pre-training Code Representations with Data Flow](https://mlsanity.com/paper/2009.08366/) (2020)
- [CodeBLEU: a Method for Automatic Evaluation of Code Synthesis](https://mlsanity.com/paper/2009.10297/) (2020)
- [Unified Pre-training for Program Understanding and Generation](https://mlsanity.com/paper/2103.06333/) (2021)
- [UniXcoder: Unified Cross-Modal Pre-training for Code Representation](https://mlsanity.com/paper/2203.03850/) (2022)
- [Unsupervised Translation of Programming Languages](https://mlsanity.com/paper/2006.03511/) (2020)
- [CodeNet: A Large-Scale AI for Code Dataset for Learning a Diversity of Coding Tasks](https://mlsanity.com/paper/2105.12655/) (2021)
- [Unsupervised Neural Machine Translation](https://mlsanity.com/paper/1710.11041/) (2017)
- [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)
- [XLCoST: A Benchmark Dataset for Cross-lingual Code Intelligence](https://mlsanity.com/paper/2206.08474/) (2022)
- [StructCoder: Structure-Aware Transformer for Code Generation](https://mlsanity.com/paper/2206.05239/) (2022)

## Built on by (most cited first, 10 of 10)

- [Learning to Focus: Causal Attention Distillation via Gradient-Guided Token Pruning](https://mlsanity.com/paper/2506.07851/) (2025)
- [AI Coders Are Among Us: Rethinking Programming Language Grammar Towards Efficient Code Generation](https://mlsanity.com/paper/2404.16333/) (2024)
- [Function-to-Style Guidance of LLMs for Code Translation](https://mlsanity.com/paper/2507.11083/) (2025)
- [On-Policy Optimization with Group Equivalent Preference for Multi-Programming Language Understanding](https://mlsanity.com/paper/2505.12723/) (2025)
- [ReasonBridge: Efficient Reasoning Transfer from Closed to Open-Source Language Models](https://mlsanity.com/paper/2506.22865/) (2025)
- [Learning Bug Context for PyTorch-to-JAX Translation with LLMs](https://mlsanity.com/paper/2510.09898/) (2025)
- [Prompt-Driven Code Summarization: A Systematic Literature Review](https://mlsanity.com/paper/2604.15385/) (2026)
- [Improving Code Translation with Syntax-Guided and Semantic-aware Preference Optimization](https://mlsanity.com/paper/2605.13229/) (2026)
- [XSearch: Explainable Code Search via Concept-to-Code Alignment](https://mlsanity.com/paper/2605.16046/) (2026)
- [ORCA: Evaluating LLMs on Data Science Code Translation](https://mlsanity.com/paper/2609.30749/) (2026)

## Abstract (arXiv)

Software version migration and program translation are an important and costly part of the lifecycle of large codebases. Traditional machine translation relies on parallel corpora for supervised translation, which is not feasible for program translation due to a dearth of aligned data. Recent unsupervised neural machine translation techniques have overcome data limitations by included techniques such as back translation and low level compiler intermediate representations (IR). These methods face significant challenges due to the noise in code snippet alignment and the diversity of IRs respectively. In this paper we propose a novel model called Code Distillation (CoDist) whereby we capture the semantic and structural equivalence of code in a language agnostic intermediate representation. Distilled code serves as a translation pivot for any programming language, leading by construction to parallel corpora which scale to all available source code by simply applying the distillation compiler. We demonstrate that our approach achieves state-of-the-art performance on CodeXGLUE and TransCoder GeeksForGeeks translation benchmarks, with an average absolute increase of 12.7% on the TransCoder GeeksforGeeks translation benchmark compare to TransCoder-ST.