RUCKBReasoning/CodeRM
Official code implementation for the ACL 2025 paper: 'Dynamic Scaling of Unit Tests for Code Reward Modeling'
This project helps software developers or researchers working with Large Language Models (LLMs) improve the quality of code generated by these models. It takes a programming problem and an LLM-generated code solution, then creates a comprehensive set of unit tests to rigorously check the solution's correctness. The output is a highly effective collection of unit tests that can be used to evaluate and select the best code from multiple LLM-generated options, even for complex coding challenges.
No commits in the last 6 months.
Use this if you need to reliably verify the correctness of code generated by AI models and want to improve the selection process for the best performing solutions.
Not ideal if you are looking for a tool to write production-ready unit tests for human-written code or for languages other than Python.
Stars
27
Forks
2
Language
Python
License
—
Category
Last pushed
May 16, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/RUCKBReasoning/CodeRM"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
agentscope-ai/Trinity-RFT
Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement...
OpenRLHF/OpenRLHF
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO &...
zjunlp/EasyEdit
[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.
huggingface/alignment-handbook
Robust recipes to align language models with human and AI preferences
hyunwoongko/nanoRLHF
nanoRLHF: from-scratch journey into how LLMs and RLHF really work.