This paper provides a principled definition for the FOL-autoformalization task by distinguishing Ontology Extraction from Logical Translation and identifies open challenges in benchmarking, semantic evaluation, ontology-aware methods, and end-to-end applications.
Abstract
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.
The participation of the HULAT-UC3M team in the TSAR 2025 Shared Task on Readability-Controlled Text Simplification is described, and their approach uses open and lightweight Large Language Models with different sizes, together with two strategies for prompt engineering.
Jesús M. Sánchez-Gómez, Lourdes Moreno, P. Martínez et al.· 0 citations
This case study assesses the feasibility of combining LLM-based extraction, metamodel-guided refinement, automated validation, and human correction for requirements formalization and evaluates the approach on the ten published ACAS Xu safety properties.
Sally Ismail, Patrick Tessier· Proceedings of the ACM/IEEE...· 0 citations
The Asset Administration Shell (AAS) enables semantic interoperability in Industry 4.0, yet the growing number of Submodel Templates (SMTs) raises concerns about their semantic quality. Due to their interdisciplinary creation, SMTs often contain inconsistencies and ambiguities, especially in open domains. However, exis...
Björn Otto, Marko Ristin, Ina Steinmetz et al.· IEEE International Conferenc...· 0 citations
Explainability for transformer-based language models is becoming crucial as these systems are deployed in high-stakes applications. As a result, the ecosystem of explainability tools is rapidly evolving, becoming richer, but also more fragmented and harder to navigate. To address this challenge, we present Virgil, an i...
Martino Ciaperoni, Sezer Kutluk, Benedetta Muscato et al.· 0 citations
Domain-specific languages bring domain experts into model-based engineering by allowing them to use their usual notation and terminology. However, developing a high-quality language with tooling often requires substantial implementation effort. Eclipse Langium is a TypeScript-based language workbench that addresses thi...
J. Meier, Steven Smyth, Benjamin Friedman Wilson et al.· Proceedings of the ACM/IEEE...· 0 citations
Related blog posts
Microsoft Research Blog· microsoft.comOct 22, 2026
Flint-interactive gives AI agents a language for creating interactive visualizations. Click a chart, filter data, highlight related content, and explore beyond the view the author originally chose. The post Flint-interactive: A language for creating interactive data visualizations appeared first on Microsoft Research.
A new computational approach reveals how cells communicate to assemble into tissues. This could accelerate stem cell engineering, improve disease models, and inform therapies.
Microsoft Research Blog· microsoft.comOct 15, 2026
Zero-knowledge proofs can verify computing results without rerunning workloads or exposing sensitive data. Magnetar helps bring them into the mainstream with support for standard programming languages, major speed gains, and quantum-resistant security. The post Proof-based general-purpose computing with Magnetar appeared first on Microsoft Research.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
