Scholarly Question Answering Using Large Language Models in the NFDI4DataScience Gateway
Research output: Contributions to collected editions/works › Article in conference proceedings › Research › peer-review
Authors
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.
| Original language | English |
|---|---|
| Title of host publication | Natural Scientific Language Processing and Research Knowledge Graphs - 1st International Workshop, NSLP 2024, Proceedings |
| Editors | Georg Rehm, Stefan Dietze, Sonja Schimmler, Frank Krüger |
| Number of pages | 16 |
| Publisher | Springer Science and Business Media Deutschland |
| Publication date | 2024 |
| Pages | 3-18 |
| ISBN (print) | 978-3-031-65793-1 |
| ISBN (electronic) | 978-3-031-65794-8 |
| DOIs | |
| Publication status | Published - 2024 |
| Event | 1st International Workshop on Natural Scientific Language Processing and Research Knowledge Graphs - NSLP 2024 - Hersonissos, Hersonissos, Greece Duration: 27.05.2024 → 27.05.2024 Conference number: 1 https://nfdi4ds.github.io/nslp2024/ |
Bibliographical note
Publisher Copyright:
© The Author(s) 2024.
- Federated Search, Large Language Models, NFDI4DS Gateway, Retrieval Augmented Generation, Scholarly Question Answering
- Informatics
- Business informatics