Gemini Pro Defeated by GPT-4V: Evidence from Education

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lee, Gyeong-Geon, Latif, Ehsan, Shi, Lehong, Zhai, Xiaoming
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929212340830208
author Lee, Gyeong-Geon
Latif, Ehsan
Shi, Lehong
Zhai, Xiaoming
author_facet Lee, Gyeong-Geon
Latif, Ehsan
Shi, Lehong
Zhai, Xiaoming
contents This study compared the classification performance of Gemini Pro and GPT-4V in educational settings. Employing visual question answering (VQA) techniques, the study examined both models' abilities to read text-based rubrics and then automatically score student-drawn models in science education. We employed both quantitative and qualitative analyses using a dataset derived from student-drawn scientific models and employing NERIF (Notation-Enhanced Rubrics for Image Feedback) prompting methods. The findings reveal that GPT-4V significantly outperforms Gemini Pro in terms of scoring accuracy and Quadratic Weighted Kappa. The qualitative analysis reveals that the differences may be due to the models' ability to process fine-grained texts in images and overall image classification performance. Even adapting the NERIF approach by further de-sizing the input images, Gemini Pro seems not able to perform as well as GPT-4V. The findings suggest GPT-4V's superior capability in handling complex multimodal educational tasks. The study concludes that while both models represent advancements in AI, GPT-4V's higher performance makes it a more suitable tool for educational applications involving multimodal data interpretation.
format Preprint
id arxiv_https___arxiv_org_abs_2401_08660
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Gemini Pro Defeated by GPT-4V: Evidence from Education
Lee, Gyeong-Geon
Latif, Ehsan
Shi, Lehong
Zhai, Xiaoming
Artificial Intelligence
Computation and Language
This study compared the classification performance of Gemini Pro and GPT-4V in educational settings. Employing visual question answering (VQA) techniques, the study examined both models' abilities to read text-based rubrics and then automatically score student-drawn models in science education. We employed both quantitative and qualitative analyses using a dataset derived from student-drawn scientific models and employing NERIF (Notation-Enhanced Rubrics for Image Feedback) prompting methods. The findings reveal that GPT-4V significantly outperforms Gemini Pro in terms of scoring accuracy and Quadratic Weighted Kappa. The qualitative analysis reveals that the differences may be due to the models' ability to process fine-grained texts in images and overall image classification performance. Even adapting the NERIF approach by further de-sizing the input images, Gemini Pro seems not able to perform as well as GPT-4V. The findings suggest GPT-4V's superior capability in handling complex multimodal educational tasks. The study concludes that while both models represent advancements in AI, GPT-4V's higher performance makes it a more suitable tool for educational applications involving multimodal data interpretation.
title Gemini Pro Defeated by GPT-4V: Evidence from Education
topic Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2401.08660