Philip Mavrepis¹, Georgios Makridis¹, Georgios Fatouros¹, Vasileios Koukos¹, Spyros Theodoropoulos¹, Maria Margarita Separdani² and Dimos Kyriazis¹, ¹University of Piraeus, Greece, ²University of Piraeus, Greece

Explainable Artificial Intelligence (XAI) is essential for making AI models transparent and understandable. However, existing XAI methods often cater to users with strong technical backgrounds, creating barriers for non-experts to comprehend these techniques. Addressing this challenge, our paper introduces "x-[plAIn]," a novel approach that enhances the accessibility of XAI through a custom Large Language Model (LLM) developed using ChatGPT Builder. The objective is to design a model capable of generating clear and concise summaries of various XAI methods, tailored to different audiences such as business professionals and academics. The key novelty of our work lies in the model's ability to adapt explanations to match each audience's knowledge level and interests, providing timely insights that facilitate informed decision-making. Results from our use-case studies demonstrate that "x-[plAIn]" effectively delivers easy-to-understand, audience-specific explanations regardless of the XAI method employed. This adaptability not only improves the accessibility of XAI but also bridges the gap between complex AI technologies and their practical applications. Our findings indicate a promising direction for leveraging LLMs to make advanced AI concepts more accessible to a diverse range of usersThe field of Explainable Artificial Intelligence (XAI) often focuses on users with a strong technical background, making it challenging for non-experts to understand XAI methods. This paper presents "x-[plAIn]", a new approach to make XAI more accessible to a wider audience through a custom Large Language Model (LLM), developed using ChatGPT Builder. Our goal was to design a model that can generate clear, concise summaries of various XAI methods, tailored for different audiences, including business professionals and academics. The key feature of our model is its ability to adapt explanations to match each audience group's knowledge level and interests. Our approach still offers timely insights, facilitating the decision-making process by the end users. Results from our use-case studies show that our model is effective in providing easy-to-understand, audience-specific explanations, regardless of the XAI method used. This adaptability improves the accessibility of XAI, bridging the gap between complex AI technologies and their practical applications. Our findings indicate a promising direction for LLMs in making advanced AI concepts more accessible to a diverse range of users.

XAI, Human-Centric Explainable AI, LLM, GPT Builder, AI