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

arXiv: https://arxiv.org/abs/2604.07116 · HTML: https://mlsanity.com/paper/2604.07116/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 29 references that are in the map.
- First posted on arXiv 8 Apr 2026.

## Builds on (most cited first, 16 of 16)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022)
- [How Much Knowledge Can You Pack Into the Parameters of a Language Model?](https://mlsanity.com/paper/2002.08910/) (2020)
- [Capabilities of GPT-4 on Medical Challenge Problems](https://mlsanity.com/paper/2303.13375/) (2023)
- [Enabling Large Language Models to Generate Text with Citations](https://mlsanity.com/paper/2305.14627/) (2023)
- [Complexity-Based Prompting for Multi-Step Reasoning](https://mlsanity.com/paper/2210.00720/) (2022)
- [Neural Text Summarization: A Critical Evaluation](https://mlsanity.com/paper/1908.08960/) (2019)
- [Do We Still Need Clinical Language Models?](https://mlsanity.com/paper/2302.08091/) (2023)
- [EHRNoteQA: An LLM Benchmark for Real-World Clinical Practice Using Discharge Summaries](https://mlsanity.com/paper/2402.16040/) (2024)
- [A Dataset for Addressing Patient's Information Needs related to Clinical Course of Hospitalization](https://mlsanity.com/paper/2506.04156/) (2025)
- [TAB-PO: Preference Optimization with a Token-Level Adaptive Barrier for Token-Critical Structured Generation](https://mlsanity.com/paper/2603.00025/) (2026)

## Abstract (arXiv)

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.