Translating Informal Proofs into Formal Proofs Using a Chain of States

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Ziyu, Yang, Bowen, Li, Chenyi, Zhang, Yuan, Zhou, Shihao, Dong, Bin, Wen, Zaiwen
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917140642136064
author Wang, Ziyu
Yang, Bowen
Li, Chenyi
Zhang, Yuan
Zhou, Shihao
Dong, Bin
Wen, Zaiwen
author_facet Wang, Ziyu
Yang, Bowen
Li, Chenyi
Zhang, Yuan
Zhou, Shihao
Dong, Bin
Wen, Zaiwen
contents We address the problem of translating informal mathematical proofs expressed in natural language into formal proofs in Lean4 under a constrained computational budget. Our approach is grounded in two key insights. First, informal proofs tend to proceed via a sequence of logical transitions - often implications or equivalences - without explicitly specifying intermediate results or auxiliary lemmas. In contrast, formal systems like Lean require an explicit representation of each proof state and the tactics that connect them. Second, each informal reasoning step can be viewed as an abstract transformation between proof states, but identifying the corresponding formal tactics often requires nontrivial domain knowledge and precise control over proof context. To bridge this gap, we propose a two stage framework. Rather than generating formal tactics directly, we first extract a Chain of States (CoS), a sequence of intermediate formal proof states aligned with the logical structure of the informal argument. We then generate tactics to transition between adjacent states in the CoS, thereby constructing the full formal proof. This intermediate representation significantly reduces the complexity of tactic generation and improves alignment with informal reasoning patterns. We build dedicated datasets and benchmarks for training and evaluation, and introduce an interactive framework to support tactic generation from formal states. Empirical results show that our method substantially outperforms existing baselines, achieving higher proof success rates.
format Preprint
id arxiv_https___arxiv_org_abs_2512_10317
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Translating Informal Proofs into Formal Proofs Using a Chain of States
Wang, Ziyu
Yang, Bowen
Li, Chenyi
Zhang, Yuan
Zhou, Shihao
Dong, Bin
Wen, Zaiwen
Logic in Computer Science
Artificial Intelligence
We address the problem of translating informal mathematical proofs expressed in natural language into formal proofs in Lean4 under a constrained computational budget. Our approach is grounded in two key insights. First, informal proofs tend to proceed via a sequence of logical transitions - often implications or equivalences - without explicitly specifying intermediate results or auxiliary lemmas. In contrast, formal systems like Lean require an explicit representation of each proof state and the tactics that connect them. Second, each informal reasoning step can be viewed as an abstract transformation between proof states, but identifying the corresponding formal tactics often requires nontrivial domain knowledge and precise control over proof context. To bridge this gap, we propose a two stage framework. Rather than generating formal tactics directly, we first extract a Chain of States (CoS), a sequence of intermediate formal proof states aligned with the logical structure of the informal argument. We then generate tactics to transition between adjacent states in the CoS, thereby constructing the full formal proof. This intermediate representation significantly reduces the complexity of tactic generation and improves alignment with informal reasoning patterns. We build dedicated datasets and benchmarks for training and evaluation, and introduce an interactive framework to support tactic generation from formal states. Empirical results show that our method substantially outperforms existing baselines, achieving higher proof success rates.
title Translating Informal Proofs into Formal Proofs Using a Chain of States
topic Logic in Computer Science
Artificial Intelligence
url https://arxiv.org/abs/2512.10317