Alternative Title

GraderGPT: Making Generative Artificial Intelligence (GenAI) Help Humans Grade Better

Contributor

University of Central Florida. Faculty Center for Teaching and Learning; University of Central Florida. Division of Digital Learning; Teaching and Learning with AI Conference (2024 : Orlando, Fla.)

Location

Seminole E

Start Date

23-7-2024 11:30 AM

End Date

23-7-2024 12:00 PM

Publisher

University of Central Florida Libraries

Keywords:

Generative AI; Grading assistance; Educational technology; Scoring variance; Writing assignments

Subjects

Grading and marking (Students)--Computer-assisted instruction; Artificial intelligence--Educational applications; Grading and marking (Students)--Evaluation; Grading and marking (Students)--Study and teaching; Academic writing--Computer-assisted instruction

Description

Generative Artificial Intelligence (GenAI) tools, such as OpenAI’s ChatGPT and Google’s Bard, have opened up a new avenue of questions, applications, and risks in the education space. Acknowledging the benefits of using such tools to assist educators, we present GraderGPT, a GenAI-based system that aims to assist in the grading quality for writing assignments in large courses with multiple graders. GraderGPT does not replace human graders but instead supports them as a powerful tool to limit scoring variance. Using two different courses as part of our initial study, preliminary feedback indicates the utility of not just identifying scoring variances, but also improving the quality of grading criteria to have better clarity and instruction. This research suggests the potential of GraderGPT as an effective GenAI grading assistant and contributes to the broader conversation about the role of GenAI in education.

Language

eng

Type

Presentation

Format

application/pdf

Rights Statement

All Rights Reserved

Audience

Faculty, Instructional designers, Administrators

Share

COinS
 
Jul 23rd, 11:30 AM Jul 23rd, 12:00 PM

GraderGPT: Making GenAI Help Humans Grade Better

Seminole E

Generative Artificial Intelligence (GenAI) tools, such as OpenAI’s ChatGPT and Google’s Bard, have opened up a new avenue of questions, applications, and risks in the education space. Acknowledging the benefits of using such tools to assist educators, we present GraderGPT, a GenAI-based system that aims to assist in the grading quality for writing assignments in large courses with multiple graders. GraderGPT does not replace human graders but instead supports them as a powerful tool to limit scoring variance. Using two different courses as part of our initial study, preliminary feedback indicates the utility of not just identifying scoring variances, but also improving the quality of grading criteria to have better clarity and instruction. This research suggests the potential of GraderGPT as an effective GenAI grading assistant and contributes to the broader conversation about the role of GenAI in education.