Publication

Abstract : Explainable Artificial Intelligence, or XAI, is gaining traction in the machine learning space because it makes AI systems easier to design and operate, boosts public trust, and makes outcomes easier to analyse. The purpose of the emerging field of XAI is to make AI models more visible and understandable. Even though explainability is being widely used in most of the black-box models these days, research is still in the development phase when it comes to introducing XAI in the retrieval systems. So, Healthcare-based retrieval systems using XAI has been concentrated in this work. XAI may provide users with an explanation of the retrieval of specific documents when they query healthcare-related materials. Patients can more easily comprehend and have faith in the advise provided when they use XAI technologies. To ensure that the logic underlying AI predictions is understandable and transparent, explainable AI models are crucial in the healthcare industry for clarifying the predictions made by medical diagnostic systems. We provide an Information Retrieval model that ranks the search results according to a relevant dimension that takes information truthfulness into consideration. To enhance the interpretability of the recovered findings and give users a justification for the scientific evidence that support the claims mentioned the retrieved documents, the system incorporates a retrieval model that utilises the explainability technique.