Scholarly Question Answering Using Large Language Models in the NFDI4DataScience Gateway
Abstract: 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.
Show BibTeX
@inproceedings{DBLP:conf/nslp/GiglouTAUUDA24,
author = {Hamed Babaei Giglou and
Tilahun Abedissa Taffa and
Rana Abdullah and
Aida Usmanova and
Ricardo Usbeck and
Jennifer D'Souza and
S{\"{o}}ren Auer},
editor = {Georg Rehm and
Stefan Dietze and
Sonja Schimmler and
Frank Kr{\"{u}}ger},
title = {Scholarly Question Answering Using Large Language Models in the NFDI4DataScience
Gateway},
booktitle = {Natural Scientific Language Processing and Research Knowledge Graphs
- First International Workshop, {NSLP} 2024, Hersonissos, Crete, Greece,
May 27, 2024, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {14770},
pages = {3--18},
publisher = {Springer},
year = {2024},
url = {https://doi.org/10.1007/978-3-031-65794-8\_1},
doi = {10.1007/978-3-031-65794-8\_1},
timestamp = {Sun, 19 Jan 2025 13:41:04 +0100},
biburl = {https://dblp.org/rec/conf/nslp/GiglouTAUUDA24.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}