WooooDyy/MathCritique
Implementation for the research paper "Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision".
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.
Stars
55
Forks
1
Language
Python
License
Apache-2.0
Category
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.
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...