Concurrent Session #3: AI-Based Grading for Small Classes
Alternative Title
Artificial Intelligence (AI)-Based Grading for Small Classes
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 (2023 : Orlando, Fla.)
Location
Cape Florida C
Start Date
24-9-2023 2:00 PM
End Date
24-9-2023 2:30 PM
Publisher
University of Central Florida Libraries
Keywords:
AI grading; Small classes; Rubric-based assessment; Large Language Model; Educational technology
Subjects
Grading and marking (Students)--Computer-assisted instruction; Artificial intelligence--Educational applications; Grading and marking (Students)--Study and teaching; Grading and marking (Students)--Data processing; Artificial intelligence--Study and teaching
Description
This proposed discussion explores the idea of AI-based grading for small classes and the challenges it poses. While AI-based grading through supervised learning has shown success in large classes, its feasibility in small classes is limited due to insufficient training data. In such cases, utilizing a detailed rubric and leveraging a Large Language Model (LLM) becomes essential. This discussion aims to investigate the effectiveness and acceptability of this approach. By examining the advantages and limitations of rubric-based grading with LLM assistance, this discussion seeks to provide insights into alternative grading methods suitable for small classes.
Language
eng
Type
Presentation
Rights Statement
All Rights Reserved
Audience
Administrators, Faculty
Recommended Citation
Shah, Piyush, "Concurrent Session #3: AI-Based Grading for Small Classes" (2023). Teaching and Learning with AI Conference Presentations. 39.
https://stars.library.ucf.edu/teachwithai/2023/sunday/39
Concurrent Session #3: AI-Based Grading for Small Classes
Cape Florida C
This proposed discussion explores the idea of AI-based grading for small classes and the challenges it poses. While AI-based grading through supervised learning has shown success in large classes, its feasibility in small classes is limited due to insufficient training data. In such cases, utilizing a detailed rubric and leveraging a Large Language Model (LLM) becomes essential. This discussion aims to investigate the effectiveness and acceptability of this approach. By examining the advantages and limitations of rubric-based grading with LLM assistance, this discussion seeks to provide insights into alternative grading methods suitable for small classes.