Learning What to Ignore: Mitigating Negative Transfer in Medical Knowledge Fusion via Clinical Task-Adaptive Selection

Xinyan Deng, Shoubin Dong, Xiaorou Zheng


Abstract
Integrating external medical knowledge into longitudinal electronic health record modeling is a prevailing paradigm to mitigate clinical data sparsity. However, existing approaches face a reliability-timeliness dilemma, struggling to balance the structural authority of static ontologies with the reasoning flexibility of large language models. Furthermore, most frameworks overlook the risk of relative negative transfer, where indiscriminately fusing task-irrelevant knowledge can introduce noise or even cause conflicts that weakens patient-specific signals. In this paper, we propose TrustKE, a Trustworthy Knowledge Enhancement framework. First, we construct a dual-layer knowledge graph that anchors dynamic, evidence-based chain-of-thought reasoning from medical literature within the stable structure of medical knowledge graph. Second, we introduce a task-adaptive knowledge selection mechanism that dynamically optimizes the graph, retaining only task-specific signals. Extensive experiments on MIMIC-III and MIMIC-IV across four clinical tasks show that TrustKE outperforms state-of-the-art baselines. Our analysis confirms that TrustKE effectively mitigates negative transfer while offering transparent reasoning for clinical decision-making.
Anthology ID:
2026.acl-long.1067
Volume:
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2026
Address:
San Diego, California, United States
Editors:
Maria Liakata, Viviane P. Moreira, Jiajun Zhang, David Jurgens
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
23295–23309
Language:
URL:
https://aclanthology.org/2026.acl-long.1067/
DOI:
10.18653/v1/2026.acl-long.1067
Bibkey:
Cite (ACL):
Xinyan Deng, Shoubin Dong, and Xiaorou Zheng. 2026. Learning What to Ignore: Mitigating Negative Transfer in Medical Knowledge Fusion via Clinical Task-Adaptive Selection. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 23295–23309, San Diego, California, United States. Association for Computational Linguistics.
Cite (Informal):
Learning What to Ignore: Mitigating Negative Transfer in Medical Knowledge Fusion via Clinical Task-Adaptive Selection (Deng et al., ACL 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.acl-long.1067.pdf
Checklist:
 2026.acl-long.1067.checklist.pdf