EUVIMEDEUVIMED entdecken
Crossref

An adaptive framework with logical query expansion and multi-step retrieval for biomedical question answering

Hoang-Quan Tran, Phong Vo, Nhung Nguyen, Van-Xuan Tran

Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology · 20.11.2026

DOI: 10.1177/18758967261508141 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology, online erschienen am 20.11.2026. Verfasst von Hoang-Quan Tran und 3 weiteren Autor:innen. Die Arbeit nennt 38 Literaturangaben. Gefördert von: Trường Đại Học Thủ Dầu Một.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Retrieval-augmented generation (RAG) has advanced biomedical question answering (QA), but existing systems are limited by single-pass retrieval and sensitivity to lexical variability in domain-specific terminology. This study proposes an adaptive RAG framework that integrates logically structured query expansion with multi-hop retrieval and reasoning to address these challenges. Queries are reformulated using a propositional conjunctive normal form to capture semantic variants while preserving logical consistency. A classification module distinguishes between single-hop and multi-hop questions, enabling adaptive processing. For complex queries, the framework performs query decomposition and generates intermediate supporting information. Retrieved documents are further refined through sentence-level segmentation and embedding-based re-ranking to identify the most relevant evidence. The approach is evaluated on the BioASQ Task B benchmark using standard metrics and RAGAS-based evaluation. Results show that the full framework achieved F1 ROUGE-2 and ROUGE-SU4 scores of 0.161 and 0.162, respectively, compared with 0.157 and 0.157 for the Naive RAG baseline, indicating modest improvements in ideal-answer quality. The framework was particularly useful for complex multi-hop questions, while simpler configurations remained competitive on several exact-answer metrics. Expert evaluation confirms that the generated answers are clear, concise, and clinically meaningful. Overall, the framework offers a practical and interpretable solution for improving biomedical QA systems.

Förderung

  • Trường Đại Học Thủ Dầu Một

Zitieren

APA

Tran, H., Vo, P., Nguyen, N., & Tran, V. (2026). An adaptive framework with logical query expansion and multi-step retrieval for biomedical question answering. Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology. https://doi.org/10.1177/18758967261508141

Vancouver

Tran H, Vo P, Nguyen N, Tran V. An adaptive framework with logical query expansion and multi-step retrieval for biomedical question answering. Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology. 2026. doi:10.1177/18758967261508141

BibTeX
@article{Tran2026,
  author = {Tran, Hoang-Quan and Vo, Phong and Nguyen, Nhung and Tran, Van-Xuan},
  title = {An adaptive framework with logical query expansion and multi-step retrieval for biomedical question answering},
  journal = {Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology},
  year = {2026},
  doi = {10.1177/18758967261508141}
}
Kostenlos starten →