A DSPy-based per-stage prompt optimization pipeline with self-consistency achieves second place among full participants in the ArchEHR-QA 2026 EHR QA shared task.
Recentresearchhasshown that LLMs can achieve near-expert performance on medical QA benchmarks (Singhal et al., 2025)
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.CL 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Neural at ArchEHR-QA 2026: One Method Fits All: Unified Prompt Optimization for Clinical QA over EHRs
A DSPy-based per-stage prompt optimization pipeline with self-consistency achieves second place among full participants in the ArchEHR-QA 2026 EHR QA shared task.