Large Language Models for Multilingual Code Intelligence: A Survey
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913070784184320 |
|---|---|
| author | Jiang, Chao Liu, Dugang Wen, Cheng Xu, Zhiwu Zheng, Hua Sadiq, Muhammad Shamsi, Jawwad Ahmed Qin, Shengchao Ming, Zhong |
| author_facet | Jiang, Chao Liu, Dugang Wen, Cheng Xu, Zhiwu Zheng, Hua Sadiq, Muhammad Shamsi, Jawwad Ahmed Qin, Shengchao Ming, Zhong |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_25960 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Large Language Models for Multilingual Code Intelligence: A Survey Jiang, Chao Liu, Dugang Wen, Cheng Xu, Zhiwu Zheng, Hua Sadiq, Muhammad Shamsi, Jawwad Ahmed Qin, Shengchao Ming, Zhong Software Engineering Machine Learning Programming Languages 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. |
| title | Large Language Models for Multilingual Code Intelligence: A Survey |
| topic | Software Engineering Machine Learning Programming Languages |
| url | https://arxiv.org/abs/2604.25960 |