Development and Testing of a Large Language Models Prompt for Natural Language Phrases Synthesis from Ontological Semantic Structures

Abstract

The article introduces an innovative approach that leverages a specially designed structured prompt for Chat GPT, a large language model. This approach was tested through a series of experiments aimed at generating natural language phrases from their underlying ontological representations. These representations were automatically derived from sentences in scientific and technical texts using advanced software tools. They encapsulate the entities identified in the text and the semantic relationships between them, which can be expressed in the sentences of the analyzed text. In more detail, the system identifies relationships between concepts and links them to entities within a sentence. These entities can be either simple sentences or parts of complex ones. The structured prompt provided to the language model includes detailed explanations of these semantic relationships and a set of concept pairs connected by these relationships, serving as the building blocks for sentence creation. The generated sentences were then compared to the original ones using the cosine similarity measure across various vectorization methods. The similarity scores, calculated using the xx_ent_wiki_sm model, ranged from 0.8193 to 0.9722. Despite these high similarity scores, some stylistic differences were noted in the generated sentences. This research holds significant practical value for the development of dialogue systems that integrate ontological methods with advanced language models, paving the way for more accurate and contextually aware information systems.