Reinforced Large Language Model is a formal theorem prover

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Luo, Zhiling
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913689196560384
author Luo, Zhiling
author_facet Luo, Zhiling
contents To take advantage of Large Language Model in theorem formalization and proof, we propose a reinforcement learning framework to iteratively optimize the pretrained LLM by rolling out next tactics and comparing them with the expected ones. The experiment results show that it helps to achieve a higher accuracy compared with directly fine-tuned LLM.
format Preprint
id arxiv_https___arxiv_org_abs_2502_08908
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Reinforced Large Language Model is a formal theorem prover
Luo, Zhiling
Artificial Intelligence
To take advantage of Large Language Model in theorem formalization and proof, we propose a reinforcement learning framework to iteratively optimize the pretrained LLM by rolling out next tactics and comparing them with the expected ones. The experiment results show that it helps to achieve a higher accuracy compared with directly fine-tuned LLM.
title Reinforced Large Language Model is a formal theorem prover
topic Artificial Intelligence
url https://arxiv.org/abs/2502.08908