{"id":"doi:10.1109/jbhi.2024.3483816","kind":"article","title":"Benchmarking Large Language Models in Evidence-Based Medicine","authors":["Jin Li","Yiyan Deng","Qi Sun","Junjie Zhu","Yu Tian","Jingsong Li","Tingting Zhu"],"author_count":7,"year":2024,"published":"2024-10-21","venue":"IEEE Journal of Biomedical and Health Informatics","cited_by":35,"doi":"10.1109/jbhi.2024.3483816","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.1109/jbhi.2024.3483816","archive_url":"https://space-kitty.com/papers/doi:10.1109/jbhi.2024.3483816","updated":null,"pmid":"39437276","pmcid":null,"openalex_id":"W4403600564","pdf_url":null,"abstract":null,"abstract_license":null,"license":null,"is_open_access":false,"retracted":false,"peer_reviewed":null,"categories":["Artificial Intelligence in Healthcare and Education"],"details":null,"provenance":"openalex","attribution":"Metadata and citation counts: OpenAlex (CC0).","topics":[{"slug":"reasoning-models","name":"Reasoning Models & Test-Time Compute","domain_slug":"ai"}],"cited_in_dossiers":[]}