用自动优化提示提升病历问答准确率，无需微调模型
Neural at ArchEHR-QA 2025: Agentic Prompt Optimization for Evidence-Grounded Clinical Question Answering
- 分两步走：先找证据句，再带引用生成答案
- 测试集得分51.5，比零样本高20分，比少样本高10分
- 适合想低成本提升医疗AI回答质量的研究者
电子健康记录（EHR）上的自动问答可缓解临床与患者的信息缺口，但需在弱监督下精准检索证据并忠实生成答案。本文提出Neural，该方法在BioNLP 2025 ArchEHR-QA共享任务中排名第二。通过将任务解耦为句子级证据识别与带显式引用的答案合成两阶段，利用DSPy的MIPROv2优化器在开发集上自动探索提示空间，联合调整指令与少量示例。引入自一致性投票机制进一步提升证据召回率，且不降低精度。在隐藏测试集上，整体得分达51.5，优于标准零样本和少样本提示分别超过20分和10分。结果表明，数据驱动的提示优化是高风险医疗问答中替代模型微调的低成本有效方案，有助于提升医疗AI助手的可靠性。
原文摘要 · Abstract (English)
Automated question answering (QA) over electronic health records (EHRs) can bridge critical information gaps for clinicians and patients, yet it demands both precise evidence retrieval and faithful answer generation under limited supervision. In this work, we present Neural, the runner-up in the BioNLP 2025 ArchEHR-QA shared task on evidence-grounded clinical QA. Our proposed method decouples the task into (1) sentence-level evidence identification and (2) answer synthesis with explicit citations. For each stage, we automatically explore the prompt space with DSPy's MIPROv2 optimizer, jointly tuning instructions and few-shot demonstrations on the development set. A self-consistency voting scheme further improves evidence recall without sacrificing precision. On the hidden test set, our method attains an overall score of 51.5, placing second stage while outperforming standard zero-shot and few-shot prompting by over 20 and 10 points, respectively. These results indicate that data-driven prompt optimization is a cost-effective alternative to model fine-tuning for high-stakes clinical QA, advancing the reliability of AI assistants in healthcare.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。