I am actively engaged in enhancing conversational agents within scientific knowledge domains, particularly focusing on the advancement of AidaBot, the Open University's conversational agent based on the AIDA Knowledge Graph. My work entails thorough exploration, learning, and experimentation with state-of-the-art methodologies, specifically leveraging the latest language models such as transformers. The primary objective is to refine communication between users and the bot, ensuring smoother interactions and more effective information exchange. Additionally, I am dedicated to enriching the AIDA Dashboard with innovative functionalities, empowering editors and researchers to navigate the scholarly landscape efficiently and derive valuable insights to inform their future strategies.

Keys: Conversational agents, Scientific knowledge graphs, Language models (Transformers), AidaBot, AIDA Dashboard

Team: Francesco Osborne, Angelo Antonio Salatino

Meloni, A., Recupero, D., Osborne, F., Salatino, A., Motta, E., Vahadati, S. and Lehmann, J. (2025) Assessing Large Language Models for SPARQL Query Generation in Scientific Question Answering, ISWC 2024 Special Session on Harmonising Generative AI and Semantic Web Technologies,, Baltimore, Maryland, USA

Lehmann, J., Meloni, A., Motta, E., Osborne, F., Recupero, D., Salatino, A.A. and Vahdati, S. (2024) Large Language Models for Scientific Question Answering: An Extensive Analysis of the SciQA Benchmark, ESWC 2024, Hersonissos, Greece

Meloni, A., Angioni, S., Salatino, A., Osborne, F., Birukou, A., Recupero, D. and Motta, E. (2023) AIDA-Bot 2.0: Enhancing Conversational Agents with Knowledge Graphs for Analysing the Research Landscape The Semantic Web - ISWC 2023, eds. Terry R., et al Payne, 14265, Springer Cham

Meloni, A., Angioni, S., Salatino, A.A., Osborne, F., Recupero, D. and Motta, E. (2023) Integrating Conversational Agents and Knowledge Graphs Within the Scholarly Domain, IEEE Access, 11, pp. 22468-22489, Institute of Electrical and Electronics Engineers (IEEE)