EUVIMEDEUVIMED entdecken
Crossref

DUAL-Know: A Description-Augmented and Uncertainty-Aware GraphRAG Framework for Anesthesiology Question Answering

Hongzhi Qi, Jianqiang Li, Yanhu Ge, Huimin Wu, Yuqi Cai, Shuyao Che, Tianqiang Sheng, Qing Zhao, Chaojin Chen

IEEE Transactions on Knowledge and Data Engineering · 2026-08 · 38 (8) · 5015-5031

DOI: 10.1109/tkde.2026.3700611 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Knowledge and Data Engineering, 2026-08. Verfasst von Hongzhi Qi und 8 weiteren Autor:innen. Die Arbeit nennt 60 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Graph-based Retrieval-Augmented Generation (GraphRAG) is a prominent technique for mitigating hallucinations in Large Language Models (LLMs), yet it faces critical limitations in high-stakes anesthesiology question answering. At the retrieval stage, pervasive synonymy and knowledge fragmentation cause clinical queries to resolve to incorrect synonym clusters, while the highly specialized and domain-specific nature of clinical language widens the semantic gap, making an effective balance between recall and precision difficult to achieve. At the reasoning stage, the high structural heterogeneity of anesthesiology knowledge graphs, combined with the strong context-dependence of clinical semantics, renders existing multi-hop reasoning susceptible to clinical logic drift along weak associations, thereby introducing unreliable reasoning paths. Finally, at the fusion stage, conflicts between retrieved evidence and the model’s parametric knowledge can easily lead to highly confident yet clinically unsafe hallucinations. To address these challenges, we propose the Description-augmented, Uncertainty-aware, and Adaptive Layered Knowledge Framework (DUAL-Know). For retrieval, query augmentation and description-augmented semantic recall bridge terminology gaps and comprehensively retrieve relevant knowledge. For reasoning, a Dynamically Gated Heterogeneous Multi-Head Attention (DGHMA) mechanism accommodates graph heterogeneity and dynamically injects query intent into each reasoning layer, followed by an uncertainty-aware path ranking module that filters noisy chains. For fusion, a multi-metric scoring strategy jointly evaluates model confidence, retrieval consistency, and semantic coherence to safely arbitrate knowledge conflicts. Experiments demonstrate that DUAL-Know consistently outperforms strong baselines, generating more accurate, reliable, and verifiable answers for complex clinical question-answering tasks.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Qi, H., Li, J., Ge, Y., Wu, H., Cai, Y., Che, S., Sheng, T., Zhao, Q., & Chen, C. (2026). DUAL-Know: A Description-Augmented and Uncertainty-Aware GraphRAG Framework for Anesthesiology Question Answering. IEEE Transactions on Knowledge and Data Engineering, 38(8), 5015-5031. https://doi.org/10.1109/tkde.2026.3700611

Vancouver

Qi H, Li J, Ge Y, Wu H, Cai Y, Che S, et al. DUAL-Know: A Description-Augmented and Uncertainty-Aware GraphRAG Framework for Anesthesiology Question Answering. IEEE Transactions on Knowledge and Data Engineering. 2026;38(8):5015-5031. doi:10.1109/tkde.2026.3700611

BibTeX
@article{Qi2026,
  author = {Qi, Hongzhi and Li, Jianqiang and Ge, Yanhu and Wu, Huimin and Cai, Yuqi and Che, Shuyao and Sheng, Tianqiang and Zhao, Qing and Chen, Chaojin},
  title = {DUAL-Know: A Description-Augmented and Uncertainty-Aware GraphRAG Framework for Anesthesiology Question Answering},
  journal = {IEEE Transactions on Knowledge and Data Engineering},
  year = {2026},
  volume = {38},
  number = {8},
  pages = {5015--5031},
  doi = {10.1109/tkde.2026.3700611}
}
Kostenlos starten →