Development and Classroom Application Research of Q&A System Based on LangChain + LLMs

As China emphasizes intelligent education, the application of Artificial Intelligence (AI) in this field is becoming increasingly widespread. Q&A systems, as one of the key technologies of AI, are gradually being integrated into classroom teaching. The application plays a significant role in improving teaching quality and promoting personalized learning. However, the application process faces several problems, such as insufficient digital literacy, the inapplicability of traditional assessment methods, and the backwardness of educational concepts and methods. Moreover, in the era of information overload, the information provided by intelligent Q&A systems may be inaccurate. To address these problems, this study developed an intelligent Q&A system based on LangChain framework and LLMs. The system creates a web interface using Streamlit, integrates with LLMs, and enables generative Q&A based on the content of PDF documents. In addition, the study further explores the application of the system in classroom teaching, aiming to change teachers' mindset, promote teachers' teaching innovation, enhance students' personalized learning experience, alleviate the problem of digital literacy deficit, and promote equity and change in education. This study not only provides a new teaching aid for educators, but also provides a practical reference for the in-depth development of smart education.

Authors

Institutions

Publication Details

Published
2024-09-13
DOI
https://doi.org/10.1109/itme63426.2024.00142
Citations
1
Primary Topic
Expert finding and Q&A systems
Type
article
Field-Weighted Citation Impact
0.78
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Development and Classroom Application Research of Q&A System Based on LangChain + LLMs

Xiuting Shao, Bingge Zhang, Ziwen Song
1 citations
Expert finding and Q&A systems
0.78
article

Development and Classroom Application Research of Q&A System Based on LangChain + LLMs

Xiuting Shao, Bingge Zhang, Ziwen Song
article en
1 citations

Abstract

As China emphasizes intelligent education, the application of Artificial Intelligence (AI) in this field is becoming increasingly widespread. Q&A systems, as one of the key technologies of AI, are gradually being integrated into classroom teaching. The application plays a significant role in improving teaching quality and promoting personalized learning. However, the application process faces several problems, such as insufficient digital literacy, the inapplicability of traditional assessment methods, and the backwardness of educational concepts and methods. Moreover, in the era of information overload, the information provided by intelligent Q&A systems may be inaccurate. To address these problems, this study developed an intelligent Q&A system based on LangChain framework and LLMs. The system creates a web interface using Streamlit, integrates with LLMs, and enables generative Q&A based on the content of PDF documents. In addition, the study further explores the application of the system in classroom teaching, aiming to change teachers' mindset, promote teachers' teaching innovation, enhance students' personalized learning experience, alleviate the problem of digital literacy deficit, and promote equity and change in education. This study not only provides a new teaching aid for educators, but also provides a practical reference for the in-depth development of smart education.

Shandong Normal University (CN)
Industry, innovation and infrastructure
Openalex Percentile: Top 17%
Expert finding and Q&A systems
0.78
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.