Domain-Specific Retrieval for Retrieval-Augmented Generation: A Case Study on Pertussis Research (Student Abstract)
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (48) · 41403-41405
DOI: 10.1609/aaai.v40i48.42286 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Hiroki Takabatake und 4 weiteren Autor:innen.
Abstract (Originalsprache)
Integrating knowledge from scientific literature is essential in biomedical research. However, the rapid growth of scientific literature makes staying up to date increasingly challenging. Retrieval-Augmented Generation (RAG) offers a promising framework, but its effectiveness in specialized biomedical domains remains unclear. In this work, we propose a two-stage retrieval pipeline for RAG, with a focus on Bordetella pertussis as a case study. Our method first applies hard filtering with synonym expansion to eliminate irrelevant passages, and then performs hybrid search, followed by reranking. We evaluate our approach using a dataset of 58 pertussis-related queries with automatic relevance judgments from multiple large language models (LLMs). Experimental results show that our pipeline improves MAP@10 by 13.4-20.4 points compared with existing methods and achieves the highest MRR@10. Furthermore, consistent improvements across different LLMs highlight the effectiveness of our approach.
Zitieren
APA
Takabatake, H., Martono, N. P., Kuwae, A., Iuchi, T., & Ohwada, H. (2026). Domain-Specific Retrieval for Retrieval-Augmented Generation: A Case Study on Pertussis Research (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 40(48), 41403-41405. https://doi.org/10.1609/aaai.v40i48.42286
Vancouver
Takabatake H, Martono NP, Kuwae A, Iuchi T, Ohwada H. Domain-Specific Retrieval for Retrieval-Augmented Generation: A Case Study on Pertussis Research (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(48):41403-41405. doi:10.1609/aaai.v40i48.42286
BibTeX
@article{Takabatake2026,
author = {Takabatake, Hiroki and Martono, Niken Prasasti and Kuwae, Asaomi and Iuchi, Toshihiko and Ohwada, Hayato},
title = {Domain-Specific Retrieval for Retrieval-Augmented Generation: A Case Study on Pertussis Research (Student Abstract)},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {48},
pages = {41403--41405},
doi = {10.1609/aaai.v40i48.42286}
}
EUVIMED