Considering the rapid improvement of large generative language models, it is important to measure their ability to encode clinical domain knowledge in order to help determine their potential utility in a clinical setting. To this end we present MedQA-SWE – a novel multiple choice, clinical question & answering (Q&A) dataset in Swedish consisting of 3,180 questions. The dataset was created from a series of exams aimed at evaluating doctors’ clinical understanding and decision making and is the first open-source clinical Q&A dataset in Swedish. The exams – originally in PDF format – were parsed and each question manually checked and curated in order to limit errors in the dataset. We provide dataset statistics along with benchmark accuracy scores of seven large generative language models on a representative sample of questions in a zero-shot setting, with some models showing impressive performance given the difficulty of the exam the dataset is based on.

“Dogwhistles” are expressions intended by the speaker have two messages: a socially-unacceptable “in-group” message understood by a subset of listeners, and a benign message intended for the out-group. We take the result of a word-replacement survey of the Swedish population intended to reveal how dogwhistles are understood, and we show that the difficulty of annotating dogwhistles is reflected in the separability in the space of a sentence-transformer Swedish BERT trained on general data.