Bridging Symbolic and Neural Reasoning: Ontology-Integrated LLMs for Domain-Grounded QA

Crystal Su

Track: Regular Track (Page limit: 6-8 pages)

Keywords: Ontology Integration, Knowledge Representation, Semantic Retrieval, Information Extraction, Interpretability, Factual Consistency

TL;DR: This paper introduces an ontology-integrated large language model framework that aligns neural generation with structured chemical engineering knowledge to improve factual accuracy, interpretability, and process control reliability.

Abstract: This work presents an ontology-integrated large language model (LLM) framework for chemical engineering that unites structured domain knowledge with generative reasoning. The proposed pipeline aligns model training and inference with the COPE ontology through a sequence of data acquisition, semantic preprocessing, information extraction, and ontology mapping steps, producing templated question-answer pairs that guide fine-tuning. A control-focused decoding stage and citation gate enforce syntactic and factual grounding by constraining outputs to ontology-linked terms, while evaluation metrics quantify both linguistic quality and ontological accuracy. Feedback and future extensions, including semantic retrieval and iterative validation, further enhance the system’s interpretability and reliability. This integration of symbolic structure and neural generation provides a transparent, auditable approach for applying LLMs to process control, safety analysis, and other critical engineering contexts.

Submission Number: 22