Neural at ArchEHR-QA 2026: One Method Fits All: Unified Prompt Optimization for Clinical QA over EHRs

TL;DR

This paper introduces Neural1.5, a modular prompt optimization approach for clinical question answering over EHRs, achieving competitive results without model fine-tuning by systematically optimizing prompts and employing self-consistency.

Contribution

The work presents a novel, modular prompt optimization framework with self-consistency and verification mechanisms for clinical QA, outperforming traditional fine-tuning methods.

Findings

Ranked second overall in the shared task

Achieved top performance in evidence identification subtask

Demonstrated cost-effectiveness compared to fine-tuning

Abstract

Automated question answering (QA) over electronic health records (EHRs) demands precise evidence retrieval, faithful answer generation, and explicit grounding of answers in clinical notes. In this work, we present Neural1.5, our method for the ArchEHR-QA 2026 shared task at CL4Health@LREC 2026, which comprises four subtasks: question interpretation, evidence identification, answer generation, and evidence alignment. Our approach decouples the task into independent, modular stages and employs DSPy"s MIPROv2 optimizer to automatically discover high-performing prompts, jointly tuning instructions and few-shot demonstrations for each stage. Within every stage, self-consistency voting over multiple stochastic inference runs suppresses spurious errors and improves reliability, while stage-specific verification mechanisms (e.g., self-reflection and chain-of-verification for alignment) further refine output quality. Among all teams that participated in all four subtasks, our method ranks second overall (mean rank 4.00), placing 4th, 1st, 4th, and 7th on Subtasks 1-4, respectively. These results demonstrate that systematic, per-stage prompt optimization combined with self-consistency mechanisms is a cost-effective alternative to model fine-tuning for multifaceted clinical QA.