Query-Conditioned Knowledge Alignment for Reliable Cross-System Medical Reasoning

TL;DR

This paper introduces Query-Conditioned Entity Alignment (QCEA), a novel approach for context-aware, asymmetric knowledge alignment across heterogeneous medical systems, improving retrieval and reasoning accuracy.

Contribution

QCEA reformulates entity alignment as a query-conditioned ranking problem, integrating semantic, graph, and direction-aware modules for better cross-system medical knowledge integration.

Findings

QCEA outperforms baselines on TCM--WM knowledge graphs.

Improved alignment enhances evidence retrieval and answer accuracy.

Results show better rank-sensitive metrics like Hit@K and MRR.

Abstract

Cross-domain knowledge alignment is essential for integrating heterogeneous medical systems, yet existing approaches typically treat entity alignment as a static matching problem, ignoring query context and cross-system asymmetry. This limitation is particularly critical in integrative medical settings, where correspondence between concepts is inherently context-dependent, non-bijective, and direction-sensitive. In this paper, we propose Query-Conditioned Entity Alignment (QCEA), which reformulates entity alignment as a query-conditioned correspondence problem. Instead of learning a fixed mapping between entity representations, QCEA treats the textual description of a source entity as a query and ranks candidate entities in the target graph, enabling context-dependent alignment. The framework integrates semantic encoding, graph-based representation learning, and a direction-aware transformation module to capture asymmetric and many-to-many correspondence across heterogeneous knowledge systems. We evaluate QCEA on TCM--WM knowledge graphs derived from SymMap, covering both symptom alignment and herb--molecule alignment tasks. Experimental results show consistent improvements over representative baselines, particularly on rank-sensitive metrics such as Hit@K and MRR. Furthermore, downstream retrieval-augmented generation (RAG) experiments demonstrate that improved alignment leads to better evidence retrieval, stronger grounding, and higher answer accuracy. These findings highlight that alignment is not merely a data integration step, but a key factor that shapes knowledge accessibility and reliability in cross-system medical reasoning.