Smart grading: A generative AI-based tool for knowledge-grounded answer evaluation in educational assessments

被引:6
|
作者
Tobler, Samuel [1 ]
机构
[1] Swiss Fed Inst Technol, Zurich, Switzerland
关键词
Artificial intelligence; Test evaluation; Educational assessment; Automated grading; GPT; Large language model;
D O I
10.1016/j.mex.2023.102531
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
Evaluating text-based answers obtained in educational settings or behavioral studies is time-consuming and resource-intensive. Applying novel artificial intelligence tools such as ChatGPT might support the process. Still, currently available implementations do not allow for automated and case-specific evaluations of large numbers of student answers. To counter this limitation, we developed a flexible software and user-friendly web application that enables researchers and educators to use cutting-edge artificial intelligence technologies by providing an interface that combines large language models with options to specify questions of interest, sample solutions, and evaluation instructions for automated answer scoring. We validated the method in an empir-ical study and found the software with expert ratings to have high reliability. Hence, the present software constitutes a valuable tool to facilitate and enhance text-based answer evaluation.center dot Generative AI-enhanced software for customizable, case-specific, and automized grading of large amounts of text-based answers.center dot Open-source software and web application for direct implementation and adaptation.
引用
收藏
页数:6
相关论文
共 10 条
  • [1] An AI-Based Evaluation Framework for Smart Building Integration into Smart City
    Shahrabani, Mustafa Muthanna Najm
    Apanaviciene, Rasa
    SUSTAINABILITY, 2024, 16 (18)
  • [2] Generative AI-based knowledge graphs for the illustration and development of mHealth self-management content
    Blanchard, Marc
    Venerito, Vincenzo
    Azevedo, Pedro Ming
    Hugle, Thomas
    FRONTIERS IN DIGITAL HEALTH, 2024, 6
  • [3] A Generative AI-based Personalized Guidance Tool for Enhancing the Feedback to MOOC Learners
    Becerra, Alvaro
    Mohseni, Zeynab
    Sanz, Javier
    Cobos, Ruth
    2024 IEEE GLOBAL ENGINEERING EDUCATION CONFERENCE, EDUCON 2024, 2024,
  • [4] Q-Module-Bot: A Generative AI-Based Question and Answer Bot for Module Teaching Support
    Allen, Mia
    Naeem, Usman
    Gill, Sukhpal Singh
    IEEE TRANSACTIONS ON EDUCATION, 2024, 67 (05) : 793 - 802
  • [5] Generative AI-based Cognitive Robot for exam candidates' knowledge self-assessment
    Haddiya, Intissar
    Pitrone, Andrea
    2024 IEEE CONFERENCE ON ARTIFICIAL INTELLIGENCE, CAI 2024, 2024, : 632 - 637
  • [6] TOWARDS EFFECTIVE ARGUMENTATION: DESIGN AND IMPLEMENTATION OF A GENERATIVE AI-BASED EVALUATION AND FEEDBACK SYSTEM
    Jho, Hunkoog
    Ha, Minsu
    JOURNAL OF BALTIC SCIENCE EDUCATION, 2024, 23 (02): : 280 - 291
  • [7] Description of Crowdsourcing and AI-Based Tool for Knowledge Management and Systems Change in Public Services
    Ulmanen, Sanna
    Hirvonen, Mari
    Tattersall, Peter
    Ristikari, Tiina
    Kuo, Vincent
    Virta, Pertti
    Jurvonen, Tanja
    Niemela, Mika
    INTERNATIONAL JOURNAL OF INNOVATION AND TECHNOLOGY MANAGEMENT, 2024, 21 (04)
  • [8] Multi-energy system smart tool for ecological water body restoration using an AI-based decision-making framework
    Xu, Shu
    Hsu, Ching-Hsien
    Montenegro-Marin, Carlos Enrique
    WATER SUPPLY, 2023, 23 (10) : 3997 - 4014
  • [9] Understanding the impact of knowledge management factors on the sustainable use of AI-based chatbots for educational purposes using a hybrid SEM-ANN approach
    Al-Sharafi, Mohammed A.
    Al-Emran, Mostafa
    Iranmanesh, Mohammad
    Al-Qaysi, Noor
    Iahad, Noorminshah A.
    Arpaci, Ibrahim
    INTERACTIVE LEARNING ENVIRONMENTS, 2023, 31 (10) : 7491 - 7510
  • [10] AI-Based Multi Sensor Fusion for Smart Decision Making: A Bi-Functional System for Single Sensor Evaluation in a Classification Task
    Zoghlami, Feryel
    Kaden, Marika
    Villmann, Thomas
    Schneider, Germar
    Heinrich, Harald
    SENSORS, 2021, 21 (13)