MIRA-Ev: A Benchmark for Granular Evidence Detection and Relational Reasoning in Clinical Exams

MIRA-Ev benchmark introduces granular evidence and argumentation evaluation for clinical NLP

MIRA-Ev is a new clinical argument mining benchmark built on Spanish medical licensing exam cases, annotated by expert clinicians with span-level premises, claims, and support/attack relations. It addresses a gap in clinical NLP evaluation where MCQA benchmarks only score final-answer accuracy, missing cases where models reach correct answers via flawed reasoning. The benchmark is released in Spanish, English, and Basque (the first clinical argumentation resource in Basque) and organizes evaluation into three tiers: evidence retrieval, argumentative component extraction, and relation classification.