A doctrine-grounded visual question answering dataset for Tactical Combat Casualty Care
This study addresses the challenge of aligning visual evidence with clinical guidelines in Tactical Combat Casualty Care (TCCC) by proposing TC3-VQA, the first doctrine-based visual question answering dataset. Methodologically, the authors employ visual annotation, passage retrieval, textual entailment verification, and multi-model validation to precisely map video observations to authoritative medical documents, thereby enabling traceable supervision of clinical reasoning. The resulting high-quality dataset comprises 1,860 question-answer pairs and has undergone rigorous review by domain experts to ensure accuracy. By establishing a robust connection between visual data and doctrinal medical knowledge, this work provides a critical benchmark resource for trustworthy visual question answering in tactical casualty care scenarios.