CoChat
Sign Up
Cited by 196Artificial Intelligence in EducationTopic ModelingIntelligent Tutoring Systems and Adaptive Learning

The DOI matches its Crossref record; 89 of the 96 references it cites were found in a registry or an index.

Retrieval-augmented generation for educational application: A systematic survey

Open access
Li, Zongxi, Wang, Zijian, Wang, Weiming, Hung, Kevin, Xie, Haoran, Wang, Fu Lee·2025·Computers and Education: Artificial Intelligence
DOI 10.1016/j.caeai.2025.100417
Open this paper in CoChat — free account

Abstract

Advancements in large language models (LLMs) have transformed AI-driven education, enabling innovative applications across various learning and teaching domains. However, LLMs still face several challenges, including hallucination and static internal knowledge, which hinder their reliability in educational settings. Retrieval-Augmented Generation (RAG) enhances LLMs by retrieving relevant information from an external knowledge base and incorporating it into the LLM's generation process. This approach improves factual accuracy and enables dynamic knowledge updates, making LLMs particularly suitable for educational applications. In this paper, we comprehensively review existing research that integrates RAG into educational scenarios. We first clarify the definition and workflow of RAG, and following the indexing mechanism of RAG, we introduce different types of retrievers and generation optimization methods. As the main focus of this work, we explore the practical applications of RAG in education, covering interactive learning systems, generation and assessment of educational content, and large-scale deployment in educational ecosystems. Based on our comprehensive review, this paper discusses existing challenges and future directions, including mitigating hallucinations, ensuring the completeness and timeliness of retrieved knowledge, reducing computational costs, and enhancing multimodal support for RAG-based educational applications.

Overview

Integrity signals

Registry

Crossref · 10.1016/j.caeai.2025.100417

Cites

89 of 89 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Citations

Cites

Show all 96 references

Research works printed but not linked: 2

  1. Ram, 2023, In-context retrieval-augmented language models, Transactions of the Association for Computational Linguistics, 11, 1316, 10.1162/tacl_a_00605 · DOI · Paper page
  2. Roemer, 2015, Altmetrics and the role of librarians, Library Technology Reports, 51, 31

Cited by

Sorted by citations

Related

See all

Metadata

Authors
Li, Z., Wang, Z., Wang, W., Hung, K., Xie, H., & Wang, F. L.
Affiliations
  • Lingnan University (HK)
  • Hong Kong Metropolitan University (HK)
Corresponding author
Li, Zongxi
ORCID
Venue
Computers and Education: Artificial Intelligence
Publisher
Elsevier BV
Published
2025-06
Volume
8
Pages
100417
ISSN
2666-920X (ISSN-L)
DOI
10.1016/j.caeai.2025.100417
OpenAlex
W4410362031
Cited by
151
References
96
Citations by year
2026: 122 · 2025: 29
FWCI
155.31
Type
journal article
Language
en
Open access
Licence
Locations
  • Computers and Education Artificial Intelligence (publishedVersion, cc-by-nc-nd)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
  • University Grants Committee (UGC/FDS16/E10/23)
  • Research Grants Council, University Grants Committee (102722)
  • Hong Kong Metropolitan University (CP/2022/02)
  • Lingnan University (SDS24A2)
Topics
  • Social Sciences › Education › Artificial Intelligence in Education
  • Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
  • Physical Sciences › Computer Science › Artificial Intelligence › Intelligent Tutoring Systems and Adaptive Learning
Keywords
retrieval-augmented generation, large language models, artificial intelligence in education, hallucination mitigation, knowledge base retrieval, interactive learning system, educational content development, automated assessment, multimodal retrieval

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review