# Large Language Models for Multilingual Code Intelligence: A Survey

arXiv: https://arxiv.org/abs/2604.25960 · HTML: https://mlsanity.com/paper/2604.25960/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 35 references that are in the map.
- First posted on arXiv 27 Apr 2026.

## Builds on (most cited first, 21 of 21)

- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation](https://mlsanity.com/paper/2102.04664/) (2021)
- [Magicoder: Empowering Code Generation with OSS-Instruct](https://mlsanity.com/paper/2312.02120/) (2023)
- [CodeNet: A Large-Scale AI for Code Dataset for Learning a Diversity of Coding Tasks](https://mlsanity.com/paper/2105.12655/) (2021)
- [HumanEval-XL: A Multilingual Code Generation Benchmark for Cross-lingual Natural Language Generalization](https://mlsanity.com/paper/2402.16694/) (2024)
- [CodeTransOcean: A Comprehensive Multilingual Benchmark for Code Translation](https://mlsanity.com/paper/2310.04951/) (2023)
- [XLCoST: A Benchmark Dataset for Cross-lingual Code Intelligence](https://mlsanity.com/paper/2206.08474/) (2022)
- [McEval: Massively Multilingual Code Evaluation](https://mlsanity.com/paper/2406.07436/) (2024)
- [IRCoder: Intermediate Representations Make Language Models Robust Multilingual Code Generators](https://mlsanity.com/paper/2403.03894/) (2024)
- [RepoTransBench: A Real-World Multilingual Benchmark for Repository-Level Code Translation](https://mlsanity.com/paper/2412.17744/) (2024)
- [Retrieval-Augmented Code Generation: A Survey with Focus on Repository-Level Approaches](https://mlsanity.com/paper/2510.04905/) (2025)
- [EvoC2Rust: A Skeleton-guided Framework for Project-Level C-to-Rust Translation](https://mlsanity.com/paper/2508.04295/) (2025)
- [InterTrans: Leveraging Transitive Intermediate Translations to Enhance LLM-based Code Translation](https://mlsanity.com/paper/2411.01063/) (2024)
- [A Comparative Study of Code Generation using ChatGPT 3.5 across 10 Programming Languages](https://mlsanity.com/paper/2308.04477/) (2023)
- [Enhancing Code Generation for Low-Resource Languages: No Silver Bullet](https://mlsanity.com/paper/2501.19085/) (2025)
- [ARCS: Agentic Retrieval-Augmented Code Synthesis with Iterative Refinement](https://mlsanity.com/paper/2504.20434/) (2025)
- [MatchFixAgent: Language-Agnostic Autonomous Repository-Level Code Translation Validation and Repair](https://mlsanity.com/paper/2509.16187/) (2025)
- [Isolating Language-Coding from Problem-Solving: Benchmarking LLMs with PseudoEval](https://mlsanity.com/paper/2502.19149/) (2025)
- [NL in the Middle: Code Translation with LLMs and Intermediate Representations](https://mlsanity.com/paper/2507.08627/) (2025)
- [Beyond Language Barriers: Multi-Agent Coordination for Multi-Language Code Generation](https://mlsanity.com/paper/2509.19918/) (2025)
- [Evaluating Large Language Models for Code Translation: Effects of Prompt Language and Prompt Design](https://mlsanity.com/paper/2509.12973/) (2025)

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

- [Large Language Models at the Intersection of Software Engineering and Software Security:An Evidence-Centered Structured Survey and Research Agenda](https://mlsanity.com/paper/2608.21107/) (2026)
- [Rethinking Pivot Programming Languages in Code Language Models](https://mlsanity.com/paper/2609.22988/) (2026)

## Abstract (arXiv)

Large language models have transformed AI-assisted software engineering, but current research remains biased toward high-resource languages such as Python, with weaker performance in languages like Rust and OCaml. Since real-world systems are inherently polyglot, robust multilingual code intelligence is crucial. This survey focuses on two key tasks: multilingual code generation from shared natural-language requirements, and multilingual code translation that preserves semantics across languages. It reviews representative methods, benchmarks, and evaluation metrics, and highlights challenges and opportunities for trustworthy cross-language generalization.