用自一致提示提升病历问答中关键句子的筛选准确率
UTSA-NLP at ArchEHR-QA 2025: Improving EHR Question Answering via Self-Consistency Prompting
- 分两步走：先找相关病历句，再生成带引用的回答
- 80亿参数模型比700亿参数模型更擅长筛选关键信息
- 自一致提示+阈值判断显著提升句子选择可靠性
我们介绍了参与 ArchEHR-QA 共享任务的系统，该任务旨在利用电子健康记录（EHR）回答临床问题。方法分两步：首先使用大语言模型从EHR中定位与医生问题相关的句子；其次基于这些句子生成简短、有引文支持的答案。通过少样本提示、自一致性和阈值筛选改进句子分类环节，以确定哪些句子至关重要。对比多个模型后发现，在识别相关信息方面，较小的80亿参数模型表现优于更大的700亿参数模型。结果表明，准确的句子选择对生成高质量回答至关重要，而自一致性结合阈值策略可使决策更可靠。
原文摘要 · Abstract (English)
We describe our system for the ArchEHR-QA Shared Task on answering clinical questions using electronic health records (EHRs). Our approach uses large language models in two steps: first, to find sentences in the EHR relevant to a clinician's question, and second, to generate a short, citation-supported response based on those sentences. We use few-shot prompting, self-consistency, and thresholding to improve the sentence classification step to decide which sentences are essential. We compare several models and find that a smaller 8B model performs better than a larger 70B model for identifying relevant information. Our results show that accurate sentence selection is critical for generating high-quality responses and that self-consistency with thresholding helps make these decisions more reliable.
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。