mukhal/GRACE
[EMNLP '23] Discriminator-Guided Chain-of-Thought Reasoning
This project helps large language models (LLMs) solve complex, multi-step reasoning problems, like advanced math or logic puzzles, more accurately. It takes an LLM's initial attempt at a solution, along with a 'discriminator' model, and guides the LLM to generate more correct, step-by-step reasoning. This is for researchers and practitioners working with LLMs on tasks requiring detailed, verifiable problem-solving.
No commits in the last 6 months.
Use this if you need to improve the accuracy and logical flow of a large language model's reasoning on challenging problems, particularly those involving calculations or sequential decision-making.
Not ideal if your primary goal is to generate creative text, summarize documents, or perform simple question-answering tasks that do not require multi-step logical deduction.
Stars
50
Forks
2
Language
Python
License
—
Category
Last pushed
Oct 11, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/mukhal/GRACE"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
open-thought/reasoning-gym
[NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards
Hmbown/Hegelion
Dialectical reasoning architecture for LLMs (Thesis → Antithesis → Synthesis)
LLM360/Reasoning360
A repo for open research on building large reasoning models
bowang-lab/BioReason
BioReason: Incentivizing Multimodal Biological Reasoning within a DNA-LLM Model | NeurIPS '25
TsinghuaC3I/Awesome-RL-for-LRMs
A Survey of Reinforcement Learning for Large Reasoning Models