jie-jw-wu/Survey-CodeLLM4LowResource-DSL

A Survey on LLM-based Code Generation for Low-Resource and Domain-Specific Programming Languages

23
/ 100
Experimental

This resource provides a comprehensive review of how Large Language Models (LLMs) perform when generating code for specialized programming languages—those with fewer existing code examples or designed for specific domains like scientific modeling or industrial automation. It synthesizes insights from over a hundred research papers, detailing what LLMs work best, effective training strategies, and how to gather necessary data. Developers, researchers, and engineers working with less common or domain-specific languages will find this useful for understanding how to apply LLMs to their coding challenges.

No commits in the last 6 months.

Use this if you are developing or evaluating LLM-powered code generation for programming languages like Rust, Haskell, Verilog, or custom domain-specific languages that are not widely used like Python or Java.

Not ideal if your primary interest is LLM-based code generation for popular, high-resource languages, as the focus here is specifically on the challenges and solutions for less common languages.

low-resource languages domain-specific languages code generation LLM applications software engineering research
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 6 / 25
Maturity 15 / 25
Community 0 / 25

How are scores calculated?

Stars

15

Forks

Language

License

MIT

Last pushed

Oct 07, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/jie-jw-wu/Survey-CodeLLM4LowResource-DSL"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.