Saved in:
Bibliographic Details
Main Authors: Zhang, Lan, Valentino, Marco, Freitas, André
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.23166
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914538558849024
author Zhang, Lan
Valentino, Marco
Freitas, André
author_facet Zhang, Lan
Valentino, Marco
Freitas, André
contents While statement autoformalization has advanced rapidly, full-theorem autoformalization remains largely unexplored. Existing iterative refinement methods in statement autoformalization typically improve isolated aspects of formalization, such as syntactic correctness, but struggle to jointly optimize multiple quality dimensions, which is critical for full-theorem autoformalization. We introduce a reference-free iterative monotonic process at inference time for full-theorem autoformalization that leverages complementary feedback from theorem provers and LLM-based judges, without access to ground-truth or existing formalizations and without human intervention. Our approach optimizes a masked composite objective over Formal Validity, Logical Preservation, Mathematical Consistency, and Formal Quality, guided by a responsiveness map that indicates how different LLMs acting as different roles preferentially improve each dimension. We further propose an acceptance policy that guarantees certified monotonic improvement, and provide conditions ensuring convergence and termination. Empirical experiments demonstrate the proposed process enables simultaneous improvement across multiple dimensions, achieving 100.00% formal validity and a 90.27% overall score on miniF2F, and 77.96% formal validity and a 52.45% overall score on ProofNet.
format Preprint
id arxiv_https___arxiv_org_abs_2601_23166
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Monotonic Reference-Free Refinement for Autoformalization
Zhang, Lan
Valentino, Marco
Freitas, André
Computation and Language
While statement autoformalization has advanced rapidly, full-theorem autoformalization remains largely unexplored. Existing iterative refinement methods in statement autoformalization typically improve isolated aspects of formalization, such as syntactic correctness, but struggle to jointly optimize multiple quality dimensions, which is critical for full-theorem autoformalization. We introduce a reference-free iterative monotonic process at inference time for full-theorem autoformalization that leverages complementary feedback from theorem provers and LLM-based judges, without access to ground-truth or existing formalizations and without human intervention. Our approach optimizes a masked composite objective over Formal Validity, Logical Preservation, Mathematical Consistency, and Formal Quality, guided by a responsiveness map that indicates how different LLMs acting as different roles preferentially improve each dimension. We further propose an acceptance policy that guarantees certified monotonic improvement, and provide conditions ensuring convergence and termination. Empirical experiments demonstrate the proposed process enables simultaneous improvement across multiple dimensions, achieving 100.00% formal validity and a 90.27% overall score on miniF2F, and 77.96% formal validity and a 52.45% overall score on ProofNet.
title Monotonic Reference-Free Refinement for Autoformalization
topic Computation and Language
url https://arxiv.org/abs/2601.23166