Scholarly Question Answering using Large Language Models in the NFDI4DataScience Gateway

• DOI: 10.48550/arxiv.2406.07257
• Publication Date: 2024-06-11
• Authors: Hamed Babaei Giglou; Tilahun Abedissa ...; Rana Abdullah; Jennifer D’Souza; Sören Auer; Aida Usmanova; Ricardo Usbeck
• Keywords: Gateway (web page); Language Modeling; Topic Modeling; Part-of-Speech Tagging; Syntax-based Translation Models; Knowledge Representation

This paper introduces a scholarly Question Answering (QA) system on top of the NFDI4DataScience Gateway, employing Retrieval Augmented Generation-based (RAG) approach. The NFDI4DS as foundational framework, offers unified and intuitive interface for querying various scientific databases using federated search. RAG-based QA, powered by Large Language Model (LLM), facilitates dynamic interaction with search results, enhancing filtering capabilities fostering conversational engagement Gateway effectiveness both QA is demonstrated through experimental analysis.