WooooDyy/MathCritique

Implementation for the research paper "Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision".

27
/ 100
Experimental

This project helps improve how Large Language Models (LLMs) solve complex problems, especially in mathematics, coding, and science. It takes an LLM's initial attempt at a complex problem and then uses a 'critique' model to give step-by-step feedback. This feedback helps refine the original LLM's reasoning and produce more accurate and diverse solutions. It's for researchers and developers working on enhancing AI models for advanced reasoning tasks.

No commits in the last 6 months.

Use this if you are a researcher or AI developer looking to significantly improve the accuracy and reasoning capabilities of your language models on challenging problems by incorporating systematic feedback.

Not ideal if you are a casual user looking for a plug-and-play solution for basic text generation, as this project is focused on deep model refinement for complex reasoning.

AI-research mathematical-reasoning LLM-fine-tuning AI-model-evaluation complex-problem-solving
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 3 / 25

How are scores calculated?

Stars

55

Forks

1

Language

Python

License

Apache-2.0

Last pushed

Nov 29, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/WooooDyy/MathCritique"

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