ReForm-Python2Dafny-Dataset

Re:Form Datasets This repository contains the datasets associated with the paper "Re:Form -- Reducing Human Priors in Scalable Formal Software Verification with RL in LLMs: A Preliminary Study on Dafny". The paper introduces a framework that leverages Reinforcement Learning (RL) within Large Language Models (LLMs) to reduce reliance on human-annotated priors for formal software verification. The datasets provided are integral for training and evaluating models in formal language… See the full description on the dataset page: https://huggingface.co/datasets/Veri-Code/ReForm-Python2Dafny-Dataset.