发表机构
University of Illinois Chicago（伊利诺伊大学芝加哥分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
UIC-AIHealth4All系统参加ArchEHR-QA 2026共享任务，针对相关子任务提出优先答案式流程等方法，在三项任务中取得对应排名，还发现模型输出可读性需优化的问题。
AI 中文摘要
我们介绍了UIC-AIHealth4All系统在ArchEHR-QA 2026（一项基于电子病历的 grounded question answering 共享任务）中的表现。我们参与了子任务2（证据识别）、子任务3（答案生成）和子任务4（答案-证据对齐）。针对子任务2和3，我们提出了优先答案式流程，该流程中模型先引用特定病历句子生成候选答案，再对完整证据集进行分类，利用了在抽象层面判断相关性与相对于生成答案判断相关性的不对称性。针对子任务4，我们对5次独立模型调用应用自一致性投票，按投票阈值保留关联。我们的流程在证据识别任务中排名第三（严格微F1值为62.90），在答案生成任务中排名第九（综合得分为31.90），在答案-证据对齐任务中排名第五（F1值为79.81）。对45种风格特征的事后语言分析显示，尽管模型输出与临床医生撰写的参考文本的词数和句子数匹配，但其可读性仍比参考文本高3.2个Flesch-Kincaid年级水平，这表明临床NLP系统的可读性需要明确优化。代码和提示可在该https URL获取。
英文摘要
We describe the UIC-AIHealth4All system for ArchEHR-QA 2026, a shared task on grounded question answering from electronic health records. We participated in Subtasks 2 (evidence identification), 3 (answer generation), and 4 (answer-evidence alignment). For Subtasks 2 and 3, we propose an answer-first pipeline in which the model generates candidate answers citing specific note sentences before classifying the full evidence set, exploiting the asymmetry between judging relevance in the abstract versus relative to a generated answer. For Subtask 4, we apply self-consistency voting over five independent model calls, retaining links by vote threshold. Our pipeline ranked third on evidence identification (Strict Micro F1 62.90), ninth on answer generation (Overall 31.90), and fifth on answer-evidence alignment (F1 79.81). A post-hoc linguistic analysis of 45 stylistic features reveals that model outputs remain 3.2 Flesch-Kincaid grade levels harder to read than clinician-authored references despite matching their word and sentence counts, suggesting readability warrants explicit optimization in clinical NLP systems. Code and prompts are available at https://github.com/mo-arvan/archehr-qa-2026-uic-aihealth4all.
Comments10 pages, 2 figures, 6 tables. System description paper for the UIC-AIHealth4All submission to the ArchEHR-QA 2026 shared task, presented at the CL4Health workshop, LREC 2026
Journal refProceedings of CL4Health @ LREC 2026
