JOURNAL ARTICLE

Letter re: Reply to the Letter to the Editor: "Can American Board of Surgery in Training Examinations Be Passed by Large Language Models? Comparative Assessment of Gemini, Copilot, and ChatGPT".

  • Published In: American Surgeon, 2026, v. 92, n. 6. P. 1863 1 of 3

  • Database: Academic Search Ultimate 2 of 3

  • Authored By: Sanli, Ahmet Necati; Tekcan Sanli, Deniz Esin 3 of 3

Abstract

The article focuses on the evaluation of large language models (LLMs) Gemini, Copilot, and ChatGPT in answering American Board of Surgery In-Training Examination (ABSITE) questions. The authors acknowledge that their study primarily assessed quantitative accuracy without analyzing the reasoning processes behind the models' responses, noting this as a limitation and suggesting future research incorporate justification-based or chain-of-thought analyses. They also address feedback regarding statistical methods, agreeing to use more rigorous paired-data tests such as Cochran's Q and McNemar tests in subsequent analyses. The authors emphasize the importance of multidimensional evaluation to better understand the educational potential and limitations of LLMs in surgical training. [Extracted from the article]

Additional Information

  • Source:American Surgeon. 2026/06, Vol. 92, Issue 6, p1863
  • Document Type:Letter
  • Subject Area:Communication and Mass Media
  • Publication Date:2026
  • ISSN:0003-1348
  • DOI:10.1177/00031348251403577
  • Accession Number:193165249
  • Copyright Statement:Copyright of American Surgeon is the property of Sage Publications Inc. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Looking to go deeper into this topic? Look for more articles on EBSCOhost.