martin-wey/CodeUltraFeedback
CodeUltraFeedback: aligning large language models to coding preferences (TOSEM 2025)
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.
Stars
73
Forks
5
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
ExtensityAI/symbolicai
A neurosymbolic perspective on LLMs
TIGER-AI-Lab/MMLU-Pro
The code and data for "MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding...
deep-symbolic-mathematics/LLM-SR
[ICLR 2025 Oral] This is the official repo for the paper "LLM-SR" on Scientific Equation...
microsoft/interwhen
A framework for verifiable reasoning with language models.
zhudotexe/fanoutqa
Companion code for FanOutQA: Multi-Hop, Multi-Document Question Answering for Large Language...