Results 31 to 40 of about 107 (95)

Towards a Common Framework for Autoformalization

open access: yesProceedings of the AAAI Conference on Artificial Intelligence
Autoformalization has emerged as a term referring to the automation of formalization in the context of the formalization of mathematics using interactive theorem provers (proof assistants). Its rapid development has been driven by progress in deep learning, especially large language models (LLMs).
Agnieszka Mensfelt   +5 more
openaire   +3 more sources

Structure représentationnelle de l’intelligence artificielle et de ses usages en didactique de la compréhension de l’oral en français langue étrangère [PDF]

open access: yesAkofena
Résumé: Notre contribution explore la structure des représentations sociales de quatre enseignantes de français langue étrangère au sujet de l’intelligence artificielle et leurs usages en contexte scolaire.
Nawal BOUDECHICHE & Djihad MESSAADIA
doaj  

Monotonic Reference-Free Refinement for Autoformalization

open access: yesCoRR
Preprint
Lan Zhang   +2 more
openaire   +2 more sources

Reliable Evaluation and Benchmarks for Statement Autoformalization

open access: yesProceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
Accepted to EMNLP 2025. New benchmarks released, see https://github.com/augustepoiroux/RLMEval , https://huggingface.co/datasets/PAug/ProofNetSharp , and https://huggingface.co/datasets/PAug/ProofNetVerif .
Poiroux, Auguste   +3 more
openaire   +3 more sources

Consistent Autoformalization for Constructing Mathematical Libraries

open access: yesProceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
EMNLP 2024 camera ...
Lan Zhang, Xin Quan, André Freitas
openaire   +3 more sources

FormaRL: Enhancing Autoformalization with no Labeled Data

open access: yesCoRR
Autoformalization is one of the central tasks in formal verification, while its advancement remains hindered due to the data scarcity and the absence efficient methods. In this work we propose \textbf{FormaRL}, a simple yet efficient reinforcement learning framework for autoformalization which only requires a small amount of unlabeled data.
Yanxing Huang   +4 more
openaire   +2 more sources

L’autoformation d’enseignants novices, expérimentés et déserteurs comme pistes d’amélioration de la formation universitaire

open access: yesCanadian Journal of Education, 2010
Cette recherche explore et décrit l’apport de l’autoformation dans l’insertion et le maintien en emploi d’enseignants québécois aux ordres primaire et secondaire et en adaptation scolaire, ceux‐là même dont l’environnement professionnel se conjugue aux ...
Francine d’Ortun, Joanne Pharand
doaj   +2 more sources

FormalAlign: Automated Alignment Evaluation for Autoformalization

open access: yesCoRR
Autoformalization aims to convert informal mathematical proofs into machine-verifiable formats, bridging the gap between natural and formal languages. However, ensuring semantic alignment between the informal and formalized statements remains challenging. Existing approaches heavily rely on manual verification, hindering scalability.
Jianqiao Lu   +5 more
openaire   +3 more sources

PAT-Agent: Autoformalization for Model Checking

open access: yes2025 40th IEEE/ACM International Conference on Automated Software Engineering (ASE)
Accepted in ASE 2025 (International Conference on Automated Software Engineering)
Xinyue Zuo   +6 more
openaire   +3 more sources

Process-Driven Autoformalization in Lean 4

open access: yesCoRR
Autoformalization, the conversion of natural language mathematics into formal languages, offers significant potential for advancing mathematical reasoning. However, existing efforts are limited to formal languages with substantial online corpora and struggle to keep pace with rapidly evolving languages like Lean 4.
Lu, Jianqiao   +12 more
openaire   +2 more sources

Home - About - Disclaimer - Privacy