Performance Evaluation of Open-Source Large Language Models for Assisting Pathology Report Writing in Japanese

ArXi:2603.11597v1 Announce Type: cross The performance of large language models (LLMs) for ing pathology report writing in Japanese remains unexplored. We evaluated seven open-source LLMs from three perspectives: (A) generation and information extraction of pathology diagnosis text following predefined formats, (B) correction of typographical errors in Japanese pathology reports, and (C) subjective evaluation of model-generated explanatory text by pathologists and clinicians.