Saved in:
Bibliographic Details
Main Authors: Hu, Xiaolin, Zhou, Qinghua, Grechuk, Bogdan, Tyukin, Ivan Y.
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.10558
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916816782098432
author Hu, Xiaolin
Zhou, Qinghua
Grechuk, Bogdan
Tyukin, Ivan Y.
author_facet Hu, Xiaolin
Zhou, Qinghua
Grechuk, Bogdan
Tyukin, Ivan Y.
contents Interactive theorem provers (ITPs) are powerful tools for the formal verification of mathematical proofs down to the axiom level. However, their lack of a natural language interface remains a significant limitation. Recent advancements in large language models (LLMs) have enhanced the understanding of natural language inputs, paving the way for autoformalization - the process of translating natural language proofs into formal proofs that can be verified. Despite these advancements, existing autoformalization approaches are limited to verifying complete proofs and lack the capability for finer, sentence-level verification. To address this gap, we propose StepProof, a novel autoformalization method designed for granular, step-by-step verification. StepProof breaks down complete proofs into multiple verifiable subproofs, enabling sentence-level verification. Experimental results demonstrate that StepProof significantly improves proof success rates and efficiency compared to traditional methods. Additionally, we found that minor manual adjustments to the natural language proofs, tailoring them for step-level verification, further enhanced StepProof's performance in autoformalization.
format Preprint
id arxiv_https___arxiv_org_abs_2506_10558
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle StepProof: Step-by-step verification of natural language mathematical proofs
Hu, Xiaolin
Zhou, Qinghua
Grechuk, Bogdan
Tyukin, Ivan Y.
Logic in Computer Science
Artificial Intelligence
Interactive theorem provers (ITPs) are powerful tools for the formal verification of mathematical proofs down to the axiom level. However, their lack of a natural language interface remains a significant limitation. Recent advancements in large language models (LLMs) have enhanced the understanding of natural language inputs, paving the way for autoformalization - the process of translating natural language proofs into formal proofs that can be verified. Despite these advancements, existing autoformalization approaches are limited to verifying complete proofs and lack the capability for finer, sentence-level verification. To address this gap, we propose StepProof, a novel autoformalization method designed for granular, step-by-step verification. StepProof breaks down complete proofs into multiple verifiable subproofs, enabling sentence-level verification. Experimental results demonstrate that StepProof significantly improves proof success rates and efficiency compared to traditional methods. Additionally, we found that minor manual adjustments to the natural language proofs, tailoring them for step-level verification, further enhanced StepProof's performance in autoformalization.
title StepProof: Step-by-step verification of natural language mathematical proofs
topic Logic in Computer Science
Artificial Intelligence
url https://arxiv.org/abs/2506.10558