medical QA

all-processed dataset is a concatenation of of medical-meadow-* and chatdoctor_healthcaremagic datasets The Chat Doctor term is replaced by the chatbot term in the chatdoctor_healthcaremagic dataset Similar to the literature the medical_meadow_cord19 dataset is subsampled to 50,000 samples truthful-qa-* is a benchmark

Papers using medical QA (2)

Confidence Calibration for Multimodal LLMs: An Empirical Study through Medical VQA2026Select to Know: An Internal-External Knowledge Self-Selection Framework for Domain-Specific Question Answering2025