Consistent Autoformalization for Constructing Mathematical Libraries

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Lan, Quan, Xin, Freitas, Andre
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912427722932224
author Zhang, Lan
Quan, Xin
Freitas, Andre
author_facet Zhang, Lan
Quan, Xin
Freitas, Andre
contents Autoformalization is the task of automatically translating mathematical content written in natural language to a formal language expression. The growing language interpretation capabilities of Large Language Models (LLMs), including in formal languages, are lowering the barriers for autoformalization. However, LLMs alone are not capable of consistently and reliably delivering autoformalization, in particular as the complexity and specialization of the target domain grows. As the field evolves into the direction of systematically applying autoformalization towards large mathematical libraries, the need to improve syntactic, terminological and semantic control increases. This paper proposes the coordinated use of three mechanisms, most-similar retrieval augmented generation (MS-RAG), denoising steps, and auto-correction with syntax error feedback (Auto-SEF) to improve autoformalization quality. The empirical analysis, across different models, demonstrates that these mechanisms can deliver autoformalizaton results which are syntactically, terminologically and semantically more consistent. These mechanisms can be applied across different LLMs and have shown to deliver improve results across different model types.
format Preprint
id arxiv_https___arxiv_org_abs_2410_04194
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Consistent Autoformalization for Constructing Mathematical Libraries
Zhang, Lan
Quan, Xin
Freitas, Andre
Computation and Language
Formal Languages and Automata Theory
Autoformalization is the task of automatically translating mathematical content written in natural language to a formal language expression. The growing language interpretation capabilities of Large Language Models (LLMs), including in formal languages, are lowering the barriers for autoformalization. However, LLMs alone are not capable of consistently and reliably delivering autoformalization, in particular as the complexity and specialization of the target domain grows. As the field evolves into the direction of systematically applying autoformalization towards large mathematical libraries, the need to improve syntactic, terminological and semantic control increases. This paper proposes the coordinated use of three mechanisms, most-similar retrieval augmented generation (MS-RAG), denoising steps, and auto-correction with syntax error feedback (Auto-SEF) to improve autoformalization quality. The empirical analysis, across different models, demonstrates that these mechanisms can deliver autoformalizaton results which are syntactically, terminologically and semantically more consistent. These mechanisms can be applied across different LLMs and have shown to deliver improve results across different model types.
title Consistent Autoformalization for Constructing Mathematical Libraries
topic Computation and Language
Formal Languages and Automata Theory
url https://arxiv.org/abs/2410.04194