The ARMADA – reliAble conveRsational doMAin-specific Data exploration and Analysis – doctoral network aims at training 15 versatile and interconnected Early-Stage Researchers (ESRs) to specialise in the overarching area of Conversational Artificial Intelligence (Conversational AI) and the challenges associated to the recent advances in developing Large Language Models (LLMs). These specialists will acquire unique knowledge and skills in Artificial Intelligence, Natural Language Processing, Machine Learning, Data Management, and Algorithm Design to improve the reliability of LLMs.

A reliable LLM will produce timely, consistent, and verifiable answers, and provide guidance to the user. Recognising the multifaceted challenges and opportunities associated with domain-specific utilisation of LLMs, ARMADA's research vision starts from the design of a reliable and domain-specific question answering platform that will augment large language models with factuality, interpretability, soundness, and guidance capabilities.

The platform will cater to three domain-specific use cases: educational, medical, and business intelligence, encompassing different types of data, including images, tabular data, text data, and knowledge graphs.