Facilitating university admission using a chatbot based on large language models with retrieval-augmented generation

University admission consultation is a professional service that assists students with the university application process. Typically, accessing this service entails exploring university websites, directly contacting faculty members and officers via phone calls or emails, and engaging educational int...

Full description

Saved in:
Bibliographic Details
Main Authors: Zheng Chen, Di Zou, Haoran Xie, Huajie Lou, Zhiyuan Pang
Format: Article
Language:English
Published: International Forum of Educational Technology & Society 2024-10-01
Series:Educational Technology & Society
Subjects:
Online Access:https://www.j-ets.net/collection/published-issues/27_4#h.31gs75qaf1rj
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850203453904650240
author Zheng Chen
Di Zou
Haoran Xie
Huajie Lou
Zhiyuan Pang
author_facet Zheng Chen
Di Zou
Haoran Xie
Huajie Lou
Zhiyuan Pang
author_sort Zheng Chen
collection DOAJ
description University admission consultation is a professional service that assists students with the university application process. Typically, accessing this service entails exploring university websites, directly contacting faculty members and officers via phone calls or emails, and engaging educational intermediaries. University admission consultation is crucial for both students and institutions. However, conventional consultation methods face challenges such as time and spatial constraints, leading to a growing interest in utilizing chatbots for university admission consultation. In this study, we propose a novel approach that leverages generative pretrained transformer (ChatGPT 3.5) models and implements the retrieval-augmented generation technique using the LlamaIndex framework. To evaluate the effectiveness of this approach, we applied it to undergraduate admission data from three universities: a science and technology university in the United States, a comprehensive university in Kenya, and a comprehensive university in Hong Kong. We also gathered feedback from 53 high school students who tested the chatbot. The results demonstrated a significant improvement in average accuracy, from 41.4% with the ChatGPT 3.5 model to 89.5% with the proposed chatbot, with peak accuracy reaching 94.7%. User reviews also indicated a generally positive perception of the admission chatbot. This methodology has the potential to revolutionize university admissions by utilizing chatbots based on large language models with retrieval-augmented generation.
format Article
id doaj-art-1def23f23c554d11a962e11b2399a49e
institution OA Journals
issn 1176-3647
1436-4522
language English
publishDate 2024-10-01
publisher International Forum of Educational Technology & Society
record_format Article
series Educational Technology & Society
spelling doaj-art-1def23f23c554d11a962e11b2399a49e2025-08-20T02:11:30ZengInternational Forum of Educational Technology & SocietyEducational Technology & Society1176-36471436-45222024-10-01274454470https://doi.org/10.30191/ETS.202410_27(4).TP02Facilitating university admission using a chatbot based on large language models with retrieval-augmented generationZheng Chen0Di Zou1Haoran Xie2Huajie Lou3Zhiyuan Pang4Department of Statistics and Actuarial Science, The University of Hong Kong, Hong KongDepartment of English and Communication, The Hong Kong Polytechnic University, Hong KongSchool of Data Science, Lingnan University, Hong KongDepartment of Statistics and Actuarial Science, The University of Hong Kong, Hong KongDepartment of Statistics and Actuarial Science, The University of Hong Kong, Hong KongUniversity admission consultation is a professional service that assists students with the university application process. Typically, accessing this service entails exploring university websites, directly contacting faculty members and officers via phone calls or emails, and engaging educational intermediaries. University admission consultation is crucial for both students and institutions. However, conventional consultation methods face challenges such as time and spatial constraints, leading to a growing interest in utilizing chatbots for university admission consultation. In this study, we propose a novel approach that leverages generative pretrained transformer (ChatGPT 3.5) models and implements the retrieval-augmented generation technique using the LlamaIndex framework. To evaluate the effectiveness of this approach, we applied it to undergraduate admission data from three universities: a science and technology university in the United States, a comprehensive university in Kenya, and a comprehensive university in Hong Kong. We also gathered feedback from 53 high school students who tested the chatbot. The results demonstrated a significant improvement in average accuracy, from 41.4% with the ChatGPT 3.5 model to 89.5% with the proposed chatbot, with peak accuracy reaching 94.7%. User reviews also indicated a generally positive perception of the admission chatbot. This methodology has the potential to revolutionize university admissions by utilizing chatbots based on large language models with retrieval-augmented generation.https://www.j-ets.net/collection/published-issues/27_4#h.31gs75qaf1rjuniversity admissionschatbotgptlarge language modelsretrieval-augmented generation
spellingShingle Zheng Chen
Di Zou
Haoran Xie
Huajie Lou
Zhiyuan Pang
Facilitating university admission using a chatbot based on large language models with retrieval-augmented generation
Educational Technology & Society
university admissions
chatbot
gpt
large language models
retrieval-augmented generation
title Facilitating university admission using a chatbot based on large language models with retrieval-augmented generation
title_full Facilitating university admission using a chatbot based on large language models with retrieval-augmented generation
title_fullStr Facilitating university admission using a chatbot based on large language models with retrieval-augmented generation
title_full_unstemmed Facilitating university admission using a chatbot based on large language models with retrieval-augmented generation
title_short Facilitating university admission using a chatbot based on large language models with retrieval-augmented generation
title_sort facilitating university admission using a chatbot based on large language models with retrieval augmented generation
topic university admissions
chatbot
gpt
large language models
retrieval-augmented generation
url https://www.j-ets.net/collection/published-issues/27_4#h.31gs75qaf1rj
work_keys_str_mv AT zhengchen facilitatinguniversityadmissionusingachatbotbasedonlargelanguagemodelswithretrievalaugmentedgeneration
AT dizou facilitatinguniversityadmissionusingachatbotbasedonlargelanguagemodelswithretrievalaugmentedgeneration
AT haoranxie facilitatinguniversityadmissionusingachatbotbasedonlargelanguagemodelswithretrievalaugmentedgeneration
AT huajielou facilitatinguniversityadmissionusingachatbotbasedonlargelanguagemodelswithretrievalaugmentedgeneration
AT zhiyuanpang facilitatinguniversityadmissionusingachatbotbasedonlargelanguagemodelswithretrievalaugmentedgeneration