Please use this identifier to cite or link to this item: https://repository.hneu.edu.ua/handle/123456789/40270
Title: Neuro-symbolic Formal Verification of Culinary instructions via ontology-grounded constraint satisfaction
Authors: Shaposhnyk M. V.
Minukhin S. V.
Keywords: artificial intelligence
LLM
Formal-of-Thought
DenseNet-121
Retrieval-Augmented Generation
SMT solver
Issue Date: 2026
Citation: Shaposhnyk M. V. Neuro-symbolic Formal Verification of Culinary instructions via ontology-grounded constraint satisfaction / M. V. Shaposhnyk, S. V. Minukhin // Інформаційні технології: наука, техніка, технологія, освіта, здоров’я: тези доповідей ХXХІV міжнародної науково-практичної конференції MicroCAD-2026, 13-16 травня 2026 р. – Харків: НТУ «ХПІ», 2026. – С. 1477.
Abstract: This study proposes the «Formal-of-Thought» (FoT) approach—an architecture that shifts artificial intelligence from passive generation to active formal verification using the FoodOn ontology. FoT uses large language models (LLMs) as a specification compiler, «mapping» DenseNet-121 features to FoodOn proofs using the «Retrieval-Augmented Generation» method. Safety constraints are formulated as logical predicates, and compliance with them is verified using an SMT solver.
URI: https://repository.hneu.edu.ua/handle/123456789/40270
Appears in Collections:Статті (ІС)

Files in This Item:
File Description SizeFormat 
тези MicroCAD-2026_Shaposhnyk M.V., Minukhin S.V.pdf743,73 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.