Metraipolis › archive › dc_ccaf50740324

Natural Language to First-Order Logic LLM-based Autoformalization — arXiv:2610.12030

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.12030
License (as archived)
CC0-1.0
Archived
2026-10-09T06:13:28.123Z
SHA-256 of the archived text
5b1ef78add7053455c8093165e92279c3b661d1aae54b8a154a760101507ed95
Stable URL of this page
https://metraipolis.com/documento/dc_ccaf50740324

How to cite

Natural Language to First-Order Logic LLM-based Autoformalization — arXiv:2610.12030 — arXiv (en), https://arxiv.org/abs/2610.12030 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ccaf50740324 (Metraipolis archive dc_ccaf50740324, sha256 5b1ef78add7053455c8093165e92279c3b661d1aae54b8a154a760101507ed95)
BibTeX
@misc{dcccaf50740324,
  title = {Natural Language to First-Order Logic LLM-based Autoformalization — arXiv:2610.12030},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.12030},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ccaf50740324; sha256 5b1ef78add7053455c8093165e92279c3b661d1aae54b8a154a760101507ed95},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.12030. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large Language Models (LLMs) have renewed interest in autoformalization. Yet, when First-Order Logic (FOL) is considered as the target formalism, the field still lacks a unified task formulation and a systematic survey. This paper addresses this gap: we first provide a principled definition for the FOL-autoformalization task by distinguishing Ontology Extraction from Logical Translation, showing how their conflation obscures (cross-study) evaluation; we review existing datasets, evaluation metrics, and LLM-based methods, including fine-tuning, prompting, and verification-based refinement; we identify open challenges in benchmarking, semantic evaluation, ontology-aware methods, and end-to-end applications.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.12030 — 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 2026-10-09T05:47:15.314Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).