A retrieval and knowledge-graph framework lifts rare-disease QA accuracy by 0.12 on average (0.22 for the weaker LLM, 0.02 for the stronger) on 100 BioASQ questions, reaching 0.89.
medRxiv (2023)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
A Multi-granularity Concept Sparse Activation and Hierarchical Knowledge Graph Fusion Framework for Rare Disease Diagnosis
A retrieval and knowledge-graph framework lifts rare-disease QA accuracy by 0.12 on average (0.22 for the weaker LLM, 0.02 for the stronger) on 100 BioASQ questions, reaching 0.89.