Scholarly Question Answering using Large Language Models in the NFDI4DataScience Gateway

TL;DR

This paper presents a scholarly question answering system built on the NFDI4DataScience Gateway, utilizing a Retrieval Augmented Generation approach with large language models to improve scientific database querying and interaction.

Contribution

It introduces a novel RAG-based QA system integrated with the NFDI4DS Gateway, enabling dynamic, conversational querying of scientific databases.

Findings

Effective retrieval and filtering of scientific data demonstrated

Enhanced user interaction with federated search results

Improved querying capabilities in scientific data access

Abstract

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