Preliminary communication
https://doi.org/10.31784/zvr.14.1.15
Comparison of the conceptual framework node of knowledge (NOK) with large language models (LLM)
Martina Ašenbrener Katić
; University of Rijeka, Faculty of Informatics and Digital Technologies, Rijeka, Croatia
Marina Rauker Koch
orcid.org/0000-0002-5327-2785
; University of Applied Sciences of Rijeka, Rijeka, Croatia
*
Alen Jakupović
; University of Applied Sciences of Rijeka, Rijeka, Croatia
* Corresponding author.
Abstract
A system based on the conceptual framework Node of Knowledge (NOK) enables the recording of natural language sentences and questions in the NOK relational database, as well as the retrieval of answers to those questions. Large Language Models (LLMs) are designed for the same purpose: to provide answers to questions. Therefore, comparing large language models with a system built using the Node of Knowledge conceptual framework is an important research question. This paper addresses this by comparing these two systems. Among large language models, GPT was selected for comparison as it is one of the most widely used models. The comparison was conducted in two parts. First, the process models of the two systems were compared. Second, an analysis was performed on the answers produced by the NOK-based system and by ChatGPT, representing large language models, for a selected natural language sentence and set of questions. All comparison elements revealed similarities and differences between the systems, which are presented in this paper.
Keywords
node of knowledge (NOK); knowledge representation; question answering (QA); large language model (LLM); GPT
Hrčak ID:
348185
URI
Publication date:
3.7.2026.
Visits: 0 *