Metraipolis › archive › dc_3e41de085262

MathForm: Scaling Mathematical Autoformalization with Knowledge Retrieval and Verification-Guided Refinement — arXiv:2608.14221

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.14221
License (as archived)
CC0-1.0
Archived
2026-10-19T02:20:38.399Z
SHA-256 of the archived text
a4598dafd5545490b60acbf3f3d28f811c5942b0e152cad2d013375a856ade5e
Stable URL of this page
https://metraipolis.com/documento/dc_3e41de085262

How to cite

MathForm: Scaling Mathematical Autoformalization with Knowledge Retrieval and Verification-Guided Refinement — arXiv:2608.14221 — arXiv (en), https://arxiv.org/abs/2608.14221 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3e41de085262 (Metraipolis archive dc_3e41de085262, sha256 a4598dafd5545490b60acbf3f3d28f811c5942b0e152cad2d013375a856ade5e)
BibTeX
@misc{dc3e41de085262,
  title = {MathForm: Scaling Mathematical Autoformalization with Knowledge Retrieval and Verification-Guided Refinement — arXiv:2608.14221},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.14221},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3e41de085262; sha256 a4598dafd5545490b60acbf3f3d28f811c5942b0e152cad2d013375a856ade5e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14221. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Autoformalization is commonly framed as translating natural-language mathematical statements into machine-verifiable formal languages such as Lean 4. However, faithful formalization requires more than translation. Models must map mathematical concepts to the complex hierarchy of types and definitions in formal libraries such as Mathlib, while ensuring that generated statements preserve the meaning of the source propositions. Existing approaches struggle because they rely heavily on the model's parametric memory for library-specific knowledge, while common data construction pipelines often resort to filtering single-pass outputs and lack mechanisms for feedback-driven revision. To address these challenges, we introduce MathForm, an autoformalization framework for constructing verified training data through Mathlib knowledge retrieval and verification-guided iterative refinement. Before generation, a retrieval planner gathers relevant definitions and existing formalizations from Mathlib to guide the formalization generator. Generated statements are then revised using compiler diagnostics and semantic-consistency feedback. Using this framework, we construct FormalVerse, a Lean 4 dataset containing approximately 367K verified examples across diverse mathematical domains and sources. We then train MathForm-8B through supervised fine-tuning followed by reinforcement learning. Across six benchmarks, MathForm-8B achieves average Pass@8 rates of 88.06% under Syntax Check (SC) and 72.37% under Consistency Check (CC), outperforming multiple specialized 32B autoformalizers. On the challenging FATE-H and FATE-X subsets, it attains CC pass rates of 63% and 37%, exceeding the strongest specialized baselines in both cases.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-17 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.14221 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T02:02:02.796Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).