OntoChatGPT Information System: Ontology-Driven Structured Prompts for ChatGPT Meta-Learning

Abstract

This research presents a comprehensive methodology for utilizing an ontology-driven structured prompts system in interplay with ChatGPT, a widely used large language model (LLM). The study develops formal models, both information and functional, and establishes the methodological foundations for integrating ontology-driven prompts with ChatGPT’s meta-learning capabilities. The resulting productive triad comprises the methodological foundations, advanced information technology, and the OntoChatGPT system, which collectively enhance the effectiveness and performance of chatbot systems. The implementation of this technology is demonstrated using the Ukrainian language within the domain of rehabilitation. By applying the proposed methodology, the OntoChatGPT system effectively extracts entities from contexts, classifies them, and generates relevant responses. The study highlights the versatility of the methodology, emphasizing its applicability not only to ChatGPT but also to other chatbot systems based on LLMs, such as Google’s Bard utilizing the PaLM 2 LLM. The underlying principles of meta-learning, structured prompts, and ontology-driven information retrieval form the core of the proposed methodology, enabling their adaptation and utilization in various LLM-based systems. This versatile approach opens up new possibilities for NLP and dialogue systems, empowering developers to enhance the performance and functionality of chatbot systems across different domains and languages.

Exploring the potential of ChatGPT as an adjunct for generating diagnosis based on chief complaint and cone beam CT radiologic findings

“…The prompt engineering is crucial for optimizing the performance of the LLM [ 19 ]. To enhance the accuracy and completeness of diagnostic outputs of ChatGPT, the following strategies were used:…”

Insight into the Digital Health System of Ukraine (eHealth): Trends, Definitions, Standards, and Legislative Revisions

“…The medlocalgpt project is distinctive for its integration of advanced information technology that synergizes large language models (LLMs) ( O. V. Palagin et al, 2023a ), word embeddings models ( O. V. Palagin et al, 2020 ), and aspects of ontology engineering ( K. S. Malakhov et al, 2023 ; A. Litvin et al, 2023 ; O. V. Palagin et al, 2023b , 2023c ). This includes the utilization of SPARQL or SQL for precise database queries, facilitating the retrieval of fully structured information, and the innovative application of prompt tuning to LLMs, incorporating selected domain-specific knowledge.…”

Ontology-Driven Computer Systems

“…Within this subsystem, formal-logical translation of the sentences and the collective text is executed, typically transforming the text into an appropriate first-order formal theory. A common technique includes an intermediary phase where data is recast into modified conceptual graphs, followed by a transition into first-order predicate logic (Palagin, Kaverinskiy et al, 2023). The LOMW's formulation is exhaustively dissected in Palagin (2016), and Palagin (2006) furnishes intricate details about the SOMW's development.…”

“…This paradigm aims to offer a unified blueprint and guiding principles for systematic knowledge depiction, categorisation, and interlinking, irrespective of the domain of expertise. The advent of ontological strategies has enabled the effective construction of knowledge-centric systems and, crucially, laid the foundation for trans-disciplinary engagement and ontological engineering within the realm of contemporary AI (Gómez-Pérez et al, 2004;Guarino, 1998;Palagin, Kaverinskiy et al, 2023;Sowa, 2000;Staab & Studer, 2009).…”