GAP constructs a patient-centric graph from dialogue and generates knowledge-grounded prompts, achieving 39.28 Jaccard on DialMed, above LLM-based baselines but below the supervised DDN model.
In: Findings of EMNLP
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
GAP: Graph-Assisted Prompts for Dialogue-based Medication Recommendation
GAP constructs a patient-centric graph from dialogue and generates knowledge-grounded prompts, achieving 39.28 Jaccard on DialMed, above LLM-based baselines but below the supervised DDN model.