CoChat

Tailoring Your Code Companion: Leveraging LLMs and RAG to Develop a Chatbot to Support Students in a Programming Course

Alario-Hoyos, Carlos, Kemcha, Rebiha, Kloos, Carlos Delgado, Callejo, Patricia, Estévez-Ayres, Iria, Santín-Cristóbal, David, Cruz-Argudo, Francisco, López-Sánchez, José Luis · 2024 · 2024 IEEE International Conference on Teaching, Assessment and Learning for Engineering (TALE)

The DOI matches its Crossref record; 37 of the 37 references it cites were found in a registry or an index.

Abstract

Students frequently rely on chatbots powered by generative Artificial Intelligence (GenAI), such as ChatGPT, Copilot, Gemini, and Claude, to assist with a wide range of academic tasks. However, these chatbots are not specifically designed for the context of particular courses, which can lead to responses that are sometimes inaccurate or insufficiently relevant. This paper introduces a chatbot specifically designed to support first-year engineering students in a Java programming course. Developed using the Retrieval-Augmented Generation (RAG) technique, the chatbot draws on course-specific resources such as videos, quizzes, programming exercises, and other materials, while using OpenAI’s Large Language Models (LLMs) GPT-4 and GPT-3.5 for information analysis and response generation. The data collected, consisting of logs from 1,059 messages sent by students to the chatbot and 30 responses to a survey, indicate that students primarily used the chatbot to clarify concepts and explain code snippets. Moreover, most of the students reported that the responses provided by the chatbot were well suited to the Java programming course.

Overview

Integrity signals

Registry

Crossref · 10.1109/tale62452.2024.10834365

Cites

37 of 37 references verified0 citation errors · 0 not checkable

Statistics

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

Verification

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

Cites

Show all 37 references

Research works printed but not linked: 8

  1. ChatGPT
  2. Microsoft Copilot
  3. Google Gemini
  4. Claude
  5. Vision
  6. Embedding models
  7. pgvector. PostgreSQL: pgvector 0.5.0
  8. Genkinay, 2024, AI Prompt Engineering Is Dead • Long live AI prompt engineering

Cited by

See all 8

Metadata

Authors
Alario-Hoyos, C., Kemcha, R., Kloos, C. D., Callejo, P., Estévez-Ayres, I., Santín-Cristóbal, D., Cruz-Argudo, F., & López-Sánchez, J. L.
Affiliations
  • Universidad Carlos III de Madrid,Madrid,Spain
  • Universidad Carlos III de Madrid (ES)
Venue
2024 IEEE International Conference on Teaching, Assessment and Learning for Engineering (TALE)
Publisher
IEEE
Published
2024-12-09
Pages
1-8
OpenAlex
W4406417704
Cited by
8
References
34
Citations by year
2026: 5 · 2025: 3
FWCI
3.51
Type
conference paper
Language
en
Open access
closed
Locations
IEEE International Conference on Teaching, Assessment, and Learning for Engineering (publishedVersion)
Topics
  • Physical Sciences › Computer Science › Computer Science Applications › Teaching and Learning Programming
  • Social Sciences › Education › Artificial Intelligence in Education
  • Physical Sciences › Computer Science › Artificial Intelligence › Intelligent Tutoring Systems and Adaptive Learning
Keywords
chatbots, retrieval-augmented generation, large language models, programming education, Java programming, first-year engineering students, GPT-4, GPT-3.5, code explanation, student perceptions

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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Tailoring Your Code Companion: Leveraging LLMs and RAG to Develop a Chatbot to Support Students in a Programming Course. https://app.cochat.ai/papers/10.1109/tale62452.2024.10834365
The paper
Alario-Hoyos, C., Kemcha, R., Kloos, C. D., Callejo, P., Estévez-Ayres, I., Santín-Cristóbal, D., Cruz-Argudo, F., & López-Sánchez, J. L. (2024). Tailoring Your Code Companion: Leveraging LLMs and RAG to Develop a Chatbot to Support Students in a Programming Course. 2024 IEEE International Conference on Teaching, Assessment and Learning for Engineering (TALE). https://doi.org/10.1109/tale62452.2024.10834365

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.