MIRA-Ev:A Benchmark for Granular Evidence Detection and Relational Reasoning in Clinical Exams
Abstract
Clinical NLP evaluation remains dominated by multiple-choice question answering (MCQA), which scores only final-answer accuracy and cannot detect when a model reaches the correct diagnosis while grounding it in irrelevant, absent, or contradictory evidence. We introduce MIRA-Ev, a clinical argument mining benchmark built on Spanish M\'edico Interno Residente (MIR) licensing-exam cases, re-annotated by expert clinicians with span-level premises, claims, and directed support/attack relations, and released in parallel Spanish (native), English, and Basque versions, the first clinical argumentation resource in Basque. MIRA-Ev organizes evaluation into a three-tier task hierarchy: evidence sentence retrieval, argumentative component extraction, and relation classification.
Keywords
Cite
@article{arxiv.2607.19201,
title = {MIRA-Ev:A Benchmark for Granular Evidence Detection and Relational Reasoning in Clinical Exams},
author = {Iker De la Iglesia and Johanna Ramirez-Romero and Jose Maria Villa-Gonzalez and Irune Urroz García and Ander Barrena and Aitziber Atutxa},
journal= {arXiv preprint arXiv:2607.19201},
year = {2026}
}