CLIR-Bench: Benchmarking Multimodal Question Answering over Irregular Clinical Time Series
Quick Answer
CLIR-Bench is a new benchmark for multimodal question answering over irregular clinical time series, derived from de-identified ICU records.
Quick Take
CLIR-Bench is a new benchmark for multimodal question answering over irregular clinical time series, derived from de-identified ICU records. It features 6,600 QA instances across 11 clinical variables, revealing that existing models struggle with sparse clinical evidence, indicating a need for improved reasoning methods in this domain.
Key Points
- CLIR-Bench includes 6,600 QA instances organized into 11 tasks and 4 capability dimensions.
- Each question is linked to explicit temporal evidence and specific answer derivation rules.
- Existing generalist models struggle to retrieve and reason over sparse clinical evidence.
- The benchmark aims to assess models' ability to ground answers in irregular temporal observations.
- Code and data for CLIR-Bench are publicly available for further research.
Paper Resources
📖 Reader Mode
~2 min readAbstract: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). 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. 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. 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. 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.
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2607.09880 [cs.CL] |
| (or arXiv:2607.09880v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2607.09880 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jindong Han [view email]
[v1]
Fri, 10 Jul 2026 18:13:54 UTC (7,883 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CL
See more →Letting the Data Speak: Extracting Keywords from Crowdsourced Collections with AI
The study evaluates three NLP approaches—Named Entity Recognition, Keyword Extraction, and Topic Modelling—using the Their Finest Hour Online Archive to automate keyword extraction from crowdsourced WWII collections. Findings suggest that while NLP methods show promise, no single approach is sufficient, and ethical considerations in automated keyword extraction are crucial for responsible stewardship.