Intent-aware retrieval over assertion-labeled knowledge graphs improves clinical QA accuracy by 22 percentage points on a new MIMIC-IV benchmark that stresses negation, temporality, and attribution.
Clinical Knowledge Graph Construction and Evaluation with Multi-LLMs via Retrieval-Augmented Generation
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2roles
background 1polarities
background 1representative citing papers
RE-MCDF introduces a generation-verification-revision closed-loop multi-expert LLM architecture guided by a medical knowledge graph to enforce inter-disease logical constraints and outperform baselines on neurology EMR diagnosis tasks.
citing papers explorer
-
ClinicalBench: Stress-Testing Assertion-Aware Retrieval for Cross-Admission Clinical QA on MIMIC-IV
Intent-aware retrieval over assertion-labeled knowledge graphs improves clinical QA accuracy by 22 percentage points on a new MIMIC-IV benchmark that stresses negation, temporality, and attribution.
-
RE-MCDF: Closed-Loop Multi-Expert LLM Reasoning for Knowledge-Grounded Clinical Diagnosis
RE-MCDF introduces a generation-verification-revision closed-loop multi-expert LLM architecture guided by a medical knowledge graph to enforce inter-disease logical constraints and outperform baselines on neurology EMR diagnosis tasks.