Metraipolis › archive › dc_cf0f71e90f75

Autoformalization for Ambiguous Inputs: Precision, Coverage, and Cost across SQL and Logical Forms — arXiv:2611.00340

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.00340
License (as archived)
CC0-1.0
Archived
2026-11-03T18:41:35.208Z
SHA-256 of the archived text
f0c838ea248c5ed43b49224cfe7bcaeba02ae5f896fe3e09ec4654f77cb75922
Stable URL of this page
https://metraipolis.com/documento/dc_cf0f71e90f75

How to cite

Autoformalization for Ambiguous Inputs: Precision, Coverage, and Cost across SQL and Logical Forms — arXiv:2611.00340 — arXiv (en), https://arxiv.org/abs/2611.00340 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cf0f71e90f75 (Metraipolis archive dc_cf0f71e90f75, sha256 f0c838ea248c5ed43b49224cfe7bcaeba02ae5f896fe3e09ec4654f77cb75922)
BibTeX
@misc{dccf0f71e90f75,
  title = {Autoformalization for Ambiguous Inputs: Precision, Coverage, and Cost across SQL and Logical Forms — arXiv:2611.00340},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00340},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cf0f71e90f75; sha256 f0c838ea248c5ed43b49224cfe7bcaeba02ae5f896fe3e09ec4654f77cb75922},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00340. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Agentic systems translate natural-language requests into executable artifacts while managing ambiguity and inference cost. We evaluate seven autoformalization workflows on SQL and first-order logic benchmarks for ambiguous inputs. Across five SQL workflows, the raw model leads with F1 of 53.35% on AMBROSIA and 60.85% on AmbiQT. On AmP, DRIFT gains 15.98 F1 points over the raw model at 2.03 times its token cost, whereas LoC uses 18.65 times the raw model's tokens with lower F1. Within AutoCedar, structured interpretation lowers F1 by 6.44-6.95 points and raises AMBROSIA token use 2.2-fold. Paired reviewer comparisons show modest Kimi K3 gains of 1.93 points on AMBROSIA and 2.04 on AmbiQT. Clear-ambiguous AMBROSIA analysis shows greater relative stability for AutoCedar, with a smaller F1 drop than the raw model (11.46 vs. 16.68 points), alongside lower aggregate F1 (50.16% vs. 53.35%). Autoformalization alone does not guarantee robustness to ambiguity: the tested additions offer no uniformly effective remedy, making accuracy, ambiguity handling, and inference cost joint design requirements.

Tema degli esploratori: calcolo e infrastrutture (elenco arXiv cs.SE, nuovi lavori del giorno).
Categorie arXiv: Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2611.00340 — 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 2026-11-03T18:13:07.737Z dalla pagina https://arxiv.org/list/cs.SE/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).