Journal

Communication & Cognition 2024, Vol. 57, issue 3-4

ISSN

0582-2351

e-ISSN

2953-1446

Title

IMPLEMENTING LLM-BASED AI-TOOLS FOR KNOWLEDGE ASSISTANCE, TEXT AND SCENARIO ANALYSIS, AND IMAGE PROCESSING: CASE STUDIES OVERVIEW

Author

Peter Kaczmarski and Fernand Vandamme

Pages

pp. 131 - 172

Keywords

AI, Anthropic, Artificial Intelligence, chatbot, Claude-3, document summarisation, GPT-4, Google Gemini, Google Vertex AI, Hugging Face, image analysis, James Joyce, knowledge assistance, Large Language Model, LLM, OpenAI, Python, q&a, scenario analysis, speech to text, stateful chat, text sentiment, Theory of Mind (ToM), text to speech, Ulysses, web API.

Abstract

In this paper, research results are presented concerning the fastimproving capabilities of today’s Large Language Models (LLMs). The accessibility and the capabilities of state-of-the-art LLMs are illustrated based on their online versions provided by OpenAI, Google, and Anthropic. The initial focus is on accessing the LLMs via web APIs and Python client applications, and the key part of this work focuses on testing the capabilities of LLMs in tasks such as text-based q&a sessions, knowledge assistance, text- and scenario analysis, document summarisation, image interpretation, and more. Experimental results are based on top-ranked LLMs from chatbot ranking available on the Hugging Face website, which presently are GPT-4, Gemini 1.5 Pro, and Claude-3 Opus. For these 3 models, test outcomes are assessed and compared in the areas such as a stateful q&a sessions, among others concerning one of the most challenging books in English literature (“Ulysses”of James Joyce), an analysis of a false-belief Theory of Mind (ToM) scenario, and summarisation of scientific publications. In the final part, attention is given to text sentiment analysis approaches, and detailed experiments are presented concerning image description and mathematical operations on image elements carried out by the latest GPT-4o (omnium) multimodal LLM from OpenAI. Also, a literature study is provided concerning speech modules for OpenAI and Google Vertex AI LLMs. The major conclusion from this research is that fast-improving capabilities of today’s LLMs create high potential for their wide use. 132

DOI

https://doi.org/10.57028/C57-131-Z1067

Access