AcuityBench harmonizes five datasets into a four-level acuity framework to evaluate LLMs on clinical urgency identification, error patterns, and uncertainty alignment across QA and conversational formats.
(2022) The “problem” of human label variation: on ground truth in data, modeling and evaluation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
AcuityBench: Evaluating Clinical Acuity Identification and Uncertainty Alignment
AcuityBench harmonizes five datasets into a four-level acuity framework to evaluate LLMs on clinical urgency identification, error patterns, and uncertainty alignment across QA and conversational formats.