psunlpgroup/FoVer
This repository includes code and materials for the paper "Generalizable Process Reward Models via Formally Verified Training Data".
This project helps AI researchers and developers improve the reasoning abilities of large language models (LLMs). It provides a framework that automatically generates high-quality training data for Process Reward Models (PRMs). By inputting formal logic problems, it outputs precise, step-by-step error labels, allowing for more efficient and accurate LLM fine-tuning.
No commits in the last 6 months.
Use this if you are developing or fine-tuning LLMs and need a more efficient, less costly way to generate accurate supervision for improving their logical and mathematical reasoning.
Not ideal if you are a general LLM user or a practitioner looking for a ready-to-use application, as this is a developer tool for model training.
Stars
11
Forks
—
Language
Python
License
—
Category
Last pushed
Sep 30, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/psunlpgroup/FoVer"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
hud-evals/hud-python
OSS RL environment + evals toolkit
hiyouga/EasyR1
EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL
OpenRL-Lab/openrl
Unified Reinforcement Learning Framework
sail-sg/oat
🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning,...
opendilab/awesome-RLHF
A curated list of reinforcement learning with human feedback resources (continually updated)