martin-wey/CodeUltraFeedback

CodeUltraFeedback: aligning large language models to coding preferences (TOSEM 2025)

33
/ 100
Emerging

This project helps AI researchers and developers fine-tune large language models (LLMs) to generate code that better meets human preferences. It provides a dataset of complex coding instructions and corresponding LLM-generated responses, along with AI-generated feedback on qualities like readability, efficiency, and instruction-following. Researchers use this data to train LLMs that produce code more aligned with what developers expect.

No commits in the last 6 months.

Use this if you are developing or fine-tuning large language models and want them to produce code that is more human-preferred in terms of quality, style, and adherence to best practices.

Not ideal if you are looking for a tool to automatically fix bugs in existing code or generate production-ready code without further evaluation.

AI research LLM alignment code generation model fine-tuning software engineering
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

73

Forks

5

Language

Python

License

MIT

Last pushed

Jun 25, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/martin-wey/CodeUltraFeedback"

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