AI RESEARCH
EpiCurveBench: Evaluating VLMs on Epidemic Curve Digitization
arXiv CS.CL
•
ArXi:2605.27195v1 Announce Type: new Chart-to-data extraction with vision-language models (VLMs) is increasingly evaluated on benchmarks that show diminishing headroom (frontier VLMs exceed 89% on ChartQA) and with metrics that treat extracted points as unordered key-value pairs, ignoring the temporal structure of time series and penalizing small alignment shifts as catastrophic failures.