The First ACM Workshop on AI-Powered Question Answering Systems for Multimedia
Tai Tan, Quang-Linh Tran, Ly-Duyen Tran, Van-Tu Ninh, Duc‐Tien Dang‐Nguyen, Cathal Gurrin
Abstract
The advent of large language models (LLMs) has energised research in Question-Answering (QA) tasks, enabling responses across varied domains like economics and mathematics. Despite their capabilities, LLMs often lack explainability due to their complex parameter embeddings. Additionally, integrating multimedia data into QA systems introduces challenges in processing and interpreting diverse data types such as text, images, audio, and video. This necessitates sophisticated algorithms for accurate information retrieval across media while ensuring the reliability of the data and responses remains a significant challenge. The AIQAM workshop aims to bring together researchers and practitioners to address these challenges and enhance QA systems with multimedia data. The focus is on promoting innovations that improve the accuracy, explainability, and trustworthiness of QA systems, contributing to the development of the field.