Yale-DM-Lab at ArchEHR-QA 2026: Deterministic Grounding and Multi-Pass Evidence Alignment for EHR Question Answering

TL;DR

The Yale-DM-Lab system for ArchEHR-QA 2026 employs deterministic grounding and multi-pass evidence alignment, utilizing diverse models and ensemble voting to improve performance on patient-record question answering tasks.

Contribution

This work introduces a multi-model ensemble approach with evidence alignment techniques for improved EHR question answering performance.

Findings

Model diversity and ensemble voting enhance accuracy.

Using full clinician answer as context improves evidence alignment.

Alignment accuracy is mainly limited by reasoning capabilities.

Abstract

We describe the Yale-DM-Lab system for the ArchEHR-QA 2026 shared task. The task studies patient-authored questions about hospitalization records and contains four subtasks (ST): clinician-interpreted question reformulation, evidence sentence identification, answer generation, and evidence-answer alignment. ST1 uses a dual-model pipeline with Claude Sonnet 4 and GPT-4o to reformulate patient questions into clinician-interpreted questions. ST2-ST4 rely on Azure-hosted model ensembles (o3, GPT-5.2, GPT-5.1, and DeepSeek-R1) combined with few-shot prompting and voting strategies. Our experiments show three main findings. First, model diversity and ensemble voting consistently improve performance compared to single-model baselines. Second, the full clinician answer paragraph is provided as additional prompt context for evidence alignment. Third, results on the development set show that alignment accuracy is mainly limited by reasoning. The best scores on the development set reach 88.81 micro F1 on ST4, 65.72 macro F1 on ST2, 34.01 on ST3, and 33.05 on ST1.