M3 uses LLMs to translate natural language into SQL for the MIMIC-IV database, achieving 93-94% accuracy on benchmark questions with support for local privacy-preserving deployment.
Text-to-sql generation for question answering on electronic medical records
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2025 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
M3: Conversational LLMs Simplify Secure Clinical Data Access, Understanding, and Analysis
M3 uses LLMs to translate natural language into SQL for the MIMIC-IV database, achieving 93-94% accuracy on benchmark questions with support for local privacy-preserving deployment.