@inproceedings{zhang-etal-2026-inflated, title = "Inflated Excellence or True Performance? Rethinking Medical Diagnostic Benchmarks with Dynamic Evaluation", author = "Zhang, Xiangxu and Li, Lei and Zhou, Yanyun and Zhou, Xiao and Zhang, Yingying and Wu, Xian", editor = "Liakata, Maria and Moreira, Viviane P. and Zhang, Jiajun and Jurgens, David", booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)", month = jul, year = "2026", address = "San Diego, California, United States", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1218/", pages = "26454--26493", ISBN = "979-8-89176-390-6" }