{"title":"Integrating human expertise with GenAI: Insights into a collaborative feedback approach in translation education","authors":"Xueying Xu , Fangrui Sun , Wenjie Hu","doi":"10.1016/j.system.2025.103600","DOIUrl":null,"url":null,"abstract":"<div><div>The emergence of Generative AI (GenAI) has facilitated the widespread adoption of personalized feedback with greater efficiency, but also introduced potential inaccuracies and misinformation risks. To mitigate these risks, this study explores a collaborative feedback approach in translation education that integrates GenAI feedback with instructor expertise. Initially, GenAI provided personalized feedback on Chinese-to-English translation assignments. Instructors then reviewed and refined this feedback, focusing on which aspects to endorse and what modifications were necessary. To evaluate the effectiveness of this approach, we analyzed student feedback to identify the advantages and challenges of combining GenAI-generated feedback with instructor-provided insights. Firstly, the instructor-refined feedback provided insights into what GenAI can effectively achieve in providing feedback on translation assignments, as well as the areas where instructor intervention is necessary. Secondly, the study explores the benefits perceived by students regarding GenAI-instructor collaborative feedback, the comparative advantages of this feedback compared to GenAI feedback alone and its limitations. Based on the above analysis, this research highlights the potential of collaborative feedback integrating GenAI with instructor expertise and points out the areas that need attention.</div></div>","PeriodicalId":48185,"journal":{"name":"System","volume":"129 ","pages":"Article 103600"},"PeriodicalIF":4.9000,"publicationDate":"2025-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"System","FirstCategoryId":"98","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0346251X25000107","RegionNum":1,"RegionCategory":"文学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"EDUCATION & EDUCATIONAL RESEARCH","Score":null,"Total":0}
引用次数: 0
Abstract
The emergence of Generative AI (GenAI) has facilitated the widespread adoption of personalized feedback with greater efficiency, but also introduced potential inaccuracies and misinformation risks. To mitigate these risks, this study explores a collaborative feedback approach in translation education that integrates GenAI feedback with instructor expertise. Initially, GenAI provided personalized feedback on Chinese-to-English translation assignments. Instructors then reviewed and refined this feedback, focusing on which aspects to endorse and what modifications were necessary. To evaluate the effectiveness of this approach, we analyzed student feedback to identify the advantages and challenges of combining GenAI-generated feedback with instructor-provided insights. Firstly, the instructor-refined feedback provided insights into what GenAI can effectively achieve in providing feedback on translation assignments, as well as the areas where instructor intervention is necessary. Secondly, the study explores the benefits perceived by students regarding GenAI-instructor collaborative feedback, the comparative advantages of this feedback compared to GenAI feedback alone and its limitations. Based on the above analysis, this research highlights the potential of collaborative feedback integrating GenAI with instructor expertise and points out the areas that need attention.
期刊介绍:
This international journal is devoted to the applications of educational technology and applied linguistics to problems of foreign language teaching and learning. Attention is paid to all languages and to problems associated with the study and teaching of English as a second or foreign language. The journal serves as a vehicle of expression for colleagues in developing countries. System prefers its contributors to provide articles which have a sound theoretical base with a visible practical application which can be generalized. The review section may take up works of a more theoretical nature to broaden the background.