Marcel: A Lightweight and Open-Source Conversational Agent for University Student Support

Jan Trienes, Anastasiia Derzhanskaia, Roland Schwarzkopf, Markus Mühling, Jörg Schlötterer, Christin Seifert


Abstract
We present Marcel, a lightweight and open-source conversational agent designed to support prospective students with admission-related inquiries. The system aims to provide fast and personalized responses, while reducing workload of university staff. We employ retrieval-augmented generation to ground answers in university resources and to provide users with verifiable, contextually relevant information. We introduce a Frequently Asked Question (FAQ) retriever that maps user questions to knowledge-base entries, which allows administrators to steer retrieval, and improves over standard dense/hybrid retrieval strategies. The system is engineered for easy deployment in resource-constrained academic settings. We detail the system architecture, provide a technical evaluation of its components, and report insights from a real-world deployment.
Anthology ID:
2025.emnlp-demos.13
Volume:
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Ivan Habernal, Peter Schulam, Jörg Tiedemann
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
181–195
Language:
URL:
https://aclanthology.org/2025.emnlp-demos.13/
DOI:
Bibkey:
Cite (ACL):
Jan Trienes, Anastasiia Derzhanskaia, Roland Schwarzkopf, Markus Mühling, Jörg Schlötterer, and Christin Seifert. 2025. Marcel: A Lightweight and Open-Source Conversational Agent for University Student Support. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 181–195, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
Marcel: A Lightweight and Open-Source Conversational Agent for University Student Support (Trienes et al., EMNLP 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.emnlp-demos.13.pdf