Current and future state of evaluation of large language models for medical summarization tasks
Emma Croxford, Yanjun Gao, Nicholas Pellegrino, Karen Ka Yin Wong, Graham J. Wills, Elliot First, Frank Liao, Cherodeep Goswami, Brian W. Patterson, Majid Afshar · npj Health Systems · 2025
Large Language Models have expanded the potential for clinical Natural Language Generation (NLG), presenting new opportunities to manage the vast amounts of medical text. However, their use in such high-stakes environments necessitate robust evaluation workflows. In this review, we investigated the current landscape of evaluation metrics for NLG in healthcare and proposed a future direction to address the resource constraints of expert human evaluation while balancing alignment with human judgments.