AI-assisted translation in oral and maxillofacial surgery: A comparative evaluation

IF 2.4 3区医学 Q2 DENTISTRY, ORAL SURGERY & MEDICINE

Journal of Stomatology Oral and Maxillofacial Surgery Pub Date : 2026-06-01 Epub Date: 2026-01-13 DOI:10.1016/j.jormas.2026.102717

Murillo Martins Pinto , Erick Elienai Reis Araújo , Zacharie Rahhal , Dani Stanbouly , Ricardo Grillo

{"title":"AI-assisted translation in oral and maxillofacial surgery: A comparative evaluation","authors":"Murillo Martins Pinto , Erick Elienai Reis Araújo , Zacharie Rahhal , Dani Stanbouly , Ricardo Grillo","doi":"10.1016/j.jormas.2026.102717","DOIUrl":null,"url":null,"abstract":"<div><h3>Objectives</h3><div>English dominates scientific communication, yet non-native speakers face significant barriers in publishing. Artificial intelligence (AI) translation tools offer a potential solution, but their efficacy requires systematic evaluation. The aim of this paper is to evaluate the performance of generative AI tools with a focus on their suitability for non-native English-speaking researchers.</div></div><div><h3>Materials and Methods</h3><div>Thirty Non-English texts (150–300 words) across technical, academic, and descriptive genres were translated by six AI tools (ChatGPT-4.0, Claude 3.7, Copilot, Gemini 2.0, DeepSeek-V3, Perplexity) using standardized prompts. Translations were assessed via Grammarly® for correctness, clarity, engagement, and delivery. Statistical analysis (ANOVA, Kruskal-Wallis) compared performance.</div></div><div><h3>Results</h3><div>DeepSeek achieved the highest overall score (mean=92.9, <em>p</em> < 0.001), significantly outperforming Claude (<em>p</em> = 0.006) and Copilot (<em>p</em> = 0.048), while matching Gemini (<em>p</em> = 0.989). Gemini ranked second but frequently declined revisions, citing \"already perfect\" texts. Correctness varied significantly (<em>p</em> = 0.0078), with Copilot excelling, while DeepSeek led in clarity, engagement, and delivery (<em>p</em> < 0.01).</div></div><div><h3>Conclusion</h3><div>DeepSeek emerged as the most robust translator, with Gemini as a close second. AI translation can help reduce barriers but requires transparency and ongoing refinement to balance efficiency with academic rigor.</div></div>","PeriodicalId":55993,"journal":{"name":"Journal of Stomatology Oral and Maxillofacial Surgery","volume":"127 3","pages":"Article 102717"},"PeriodicalIF":2.4000,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Stomatology Oral and Maxillofacial Surgery","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2468785526000091","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2026/1/13 0:00:00","PubModel":"Epub","JCR":"Q2","JCRName":"DENTISTRY, ORAL SURGERY & MEDICINE","Score":null,"Total":0}

引用次数: 0

Abstract

Objectives

English dominates scientific communication, yet non-native speakers face significant barriers in publishing. Artificial intelligence (AI) translation tools offer a potential solution, but their efficacy requires systematic evaluation. The aim of this paper is to evaluate the performance of generative AI tools with a focus on their suitability for non-native English-speaking researchers.

Materials and Methods

Thirty Non-English texts (150–300 words) across technical, academic, and descriptive genres were translated by six AI tools (ChatGPT-4.0, Claude 3.7, Copilot, Gemini 2.0, DeepSeek-V3, Perplexity) using standardized prompts. Translations were assessed via Grammarly® for correctness, clarity, engagement, and delivery. Statistical analysis (ANOVA, Kruskal-Wallis) compared performance.

Results

DeepSeek achieved the highest overall score (mean=92.9, p < 0.001), significantly outperforming Claude (p = 0.006) and Copilot (p = 0.048), while matching Gemini (p = 0.989). Gemini ranked second but frequently declined revisions, citing "already perfect" texts. Correctness varied significantly (p = 0.0078), with Copilot excelling, while DeepSeek led in clarity, engagement, and delivery (p < 0.01).

Conclusion

DeepSeek emerged as the most robust translator, with Gemini as a close second. AI translation can help reduce barriers but requires transparency and ongoing refinement to balance efficiency with academic rigor.

查看原文本刊更多论文

人工智能辅助翻译在口腔颌面外科：比较评价。

目的：英语在科学交流中占主导地位，但非英语母语者在出版方面面临重大障碍。人工智能（AI）翻译工具提供了一个潜在的解决方案，但它们的功效需要系统的评估。本文的目的是评估生成式人工智能工具的性能，重点关注它们对非英语母语研究人员的适用性。材料和方法：使用标准化提示，通过六个人工智能工具（ChatGPT-4.0、Claude 3.7、Copilot、Gemini 2.0、DeepSeek-V3、Perplexity）翻译30个非英语文本（150-300字），涵盖技术、学术和描述性类型。通过Grammarly®评估翻译的正确性、清晰度、参与性和交付性。统计分析（ANOVA, Kruskal-Wallis）比较性能。结果：DeepSeek获得了最高的总分（平均92.9分），结论：DeepSeek成为最强大的翻译器，Gemini紧随其后。人工智能翻译可以帮助减少障碍，但需要透明度和不断改进，以平衡效率和学术严谨性。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊