CLIR-Bench: Benchmarking Multimodal Question Answering over Irregular Clinical Time Series

CLIR-Bench：针对不规则临床时间序列的多模态问答基准测试

Clinical time series are central to patient monitoring, risk assessment, and clinical decision support. However, they are often sparse, irregularly sampled, and asynchronous, making it difficult for models to identify the temporal evidence required for clinical Question Answering (QA). 临床时间序列对于患者监测、风险评估和临床决策支持至关重要。然而，这些数据通常具有稀疏性、采样不规则性和异步性，使得模型难以识别临床问答（QA）所需的时序证据。

Existing benchmarks primarily focus on regularly sampled time-series QA or medical QA over static data, and therefore rarely assess whether models can faithfully ground their answers in irregular temporal observations. 现有的基准测试主要集中在规则采样的时间序列问答或基于静态数据的医学问答上，因此很少评估模型是否能够忠实地基于不规则的时间观测结果来得出答案。

To fill this gap, we introduce CLIR-Bench, a benchmark for irregular clinical time series QA constructed from de-identified ICU records through a principled four-stage pipeline. 为了填补这一空白，我们引入了 CLIR-Bench，这是一个针对不规则临床时间序列问答的基准测试，通过一套严谨的四阶段流程，利用去标识化的 ICU 记录构建而成。

CLIR-Bench contains 6,600 QA instances spanning 11 clinical variables, organized into four capability dimensions and 11 tasks. Each question is linked to explicit temporal evidence and task-specific answer derivation rules, enabling evaluation of both answer accuracy and evidence use. CLIR-Bench 包含 6,600 个问答实例，涵盖 11 个临床变量，并组织为四个能力维度和 11 项任务。每个问题都关联了明确的时序证据和特定任务的答案推导规则，从而能够同时评估答案的准确性和证据的使用情况。

Experiments show that existing generalist models struggle to retrieve and reason over sparse clinical evidence, highlighting the need for stronger irregular time-series reasoning methods. Our code and data are available at this https URL. 实验表明，现有的通用模型在检索和推理稀疏临床证据方面表现吃力，这凸显了开发更强大的不规则时间序列推理方法的必要性。我们的代码和数据可在该链接获取。