arXiv:2608. 19981v1 Announce Type: new Abstract: We present HealMed, an expert-reviewed benchmark for multilingual evaluation of large language models in medicine.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.
arXiv:2606. 24200v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) in clinical settings increasingly requires multilingual retrieval against predominantly English evidence corpora.
arXiv:2608.22363v1 Announce Type: new Abstract: Medical visual question answering (VQA) is a crucial task in clinical AI, yet its evaluation has so far centered almost exclusively on English, limitin...
arXiv:2511.00421v2 Announce Type: replace-cross Abstract: Large language models (LLMs) show promise in medical applications, but their ability to detect and correct errors in clinical texts remains u...
arXiv:2606. 07853v1 Announce Type: cross Abstract: Large Language Models are transforming the support for clinical decision and their application in real scenarios.
The study compared the performance of the AI system Doctorina, eight physicians, and four frontier language models on 150 synthetic Polish primary‑care consultations. Doctorina achieved 82.0% top‑1 concordance, outperforming physicians (57.0%) by 25 percentage points, and also led in diagnostic workup and treatment scores. A second run confirmed these advantages across all measured outcomes.
The paper examines how multilingual medical adaptation affects the internal representations of Whisper ASR models. By comparing various fine‑tuning strategies—zero‑shot decoding, English‑only, German‑only, two‑stage EN→EN+DE, and direct EN+DE fine‑tuning—it shows that fine‑tuning significantly improves performance, with the best model varying by setting. Layer‑wise encoder analysis reveals that English medical fine‑tuning drives the main representation shift, while multilingual continuation largely preserves the adapted space, and that domain and language signals remain recoverable across layers.