Large Language Models for Multilingual Code Intelligence: A Survey
Not on the map. Why?
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.
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
21 of 35 references.
References · 21
- 2021Program Synthesis with Large Language Modelscited by 3,637
- 2021CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generationcited by 744
- 2023Magicoder: Empowering Code Generation with OSS-Instructcited by 256
- 2021CodeNet: A Large-Scale AI for Code Dataset for Learning a Diversity of Coding Taskscited by 200
- 2024HumanEval-XL: A Multilingual Code Generation Benchmark for Cross-lingual Natural Language Generalizationcited by 86
- 2023CodeTransOcean: A Comprehensive Multilingual Benchmark for Code Translationcited by 57
- 2022XLCoST: A Benchmark Dataset for Cross-lingual Code Intelligencecited by 56
- 2024McEval: Massively Multilingual Code Evaluationcited by 44
- 2024IRCoder: Intermediate Representations Make Language Models Robust Multilingual Code Generatorscited by 23
- 2024RepoTransBench: A Real-World Multilingual Benchmark for Repository-Level Code Translationcited by 23
- 2025Retrieval-Augmented Code Generation: A Survey with Focus on Repository-Level Approachescited by 23
- 2025EvoC2Rust: A Skeleton-guided Framework for Project-Level C-to-Rust Translationcited by 19
9 more
- 2024InterTrans: Leveraging Transitive Intermediate Translations to Enhance LLM-based Code Translationcited by 16
- 2023A Comparative Study of Code Generation using ChatGPT 3.5 across 10 Programming Languagescited by 12
- 2025Enhancing Code Generation for Low-Resource Languages: No Silver Bulletcited by 10
- 2025ARCS: Agentic Retrieval-Augmented Code Synthesis with Iterative Refinementcited by 7
- 2025MatchFixAgent: Language-Agnostic Autonomous Repository-Level Code Translation Validation and Repaircited by 4
- 2025Isolating Language-Coding from Problem-Solving: Benchmarking LLMs with PseudoEvalcited by 3
- 2025NL in the Middle: Code Translation with LLMs and Intermediate Representationscited by 3
- 2025Beyond Language Barriers: Multi-Agent Coordination for Multi-Language Code Generationcited by 2
- 2025Evaluating Large Language Models for Code Translation: Effects of Prompt Language and Prompt Designcited by 1
Built on by
Citing papers per year: 2026: 2.
2 papers.