Addressing Technical Challenges in Large Language Model-Driven Educational Software System
The integration of large language models (LLMs) into educational systems poses significant challenges across several key attributes, including integration, explainability, testability, and scalability. These challenges arise from the complexity of coordinating system components, difficulty interpret...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10845786/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832586837916385280 |
|---|---|
| author | Nacha Chondamrongkul Georgi Hristov Punnarumol Temdee |
| author_facet | Nacha Chondamrongkul Georgi Hristov Punnarumol Temdee |
| author_sort | Nacha Chondamrongkul |
| collection | DOAJ |
| description | The integration of large language models (LLMs) into educational systems poses significant challenges across several key attributes, including integration, explainability, testability, and scalability. These challenges arise from the complexity of coordinating system components, difficulty interpreting LLM decision-making processes, and the need for reliable, consistent model outputs in varied educational scenarios. Additionally, ensuring scalability requires robust autoscaling mechanisms and suitable architecture design to handle fluctuating workloads. This paper tackles these challenges by proposing tactics to improve system integration, enhance explainability through metadata and an algorithm process, ensure response consistency via regression testing, and facilitate efficient autoscaling through an event-driven microservice architecture. The evaluation results highlight the effectiveness of these tactics, confirming both functional consistency and robust system performance under varying loads. |
| format | Article |
| id | doaj-art-0c617a2f50544bce8ac57f8ef2911bc4 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-0c617a2f50544bce8ac57f8ef2911bc42025-01-25T00:01:12ZengIEEEIEEE Access2169-35362025-01-0113128461285810.1109/ACCESS.2025.353138010845786Addressing Technical Challenges in Large Language Model-Driven Educational Software SystemNacha Chondamrongkul0https://orcid.org/0000-0002-5344-2326Georgi Hristov1Punnarumol Temdee2https://orcid.org/0000-0001-9847-157XComputer and Communication Engineering for Capacity Building Research Center, School of Applied Digital Technology, Mae Fah Luang University, Chiang Rai, ThailandCentre of Excellence UNITe, University of Ruse, Ruse, BulgariaComputer and Communication Engineering for Capacity Building Research Center, School of Applied Digital Technology, Mae Fah Luang University, Chiang Rai, ThailandThe integration of large language models (LLMs) into educational systems poses significant challenges across several key attributes, including integration, explainability, testability, and scalability. These challenges arise from the complexity of coordinating system components, difficulty interpreting LLM decision-making processes, and the need for reliable, consistent model outputs in varied educational scenarios. Additionally, ensuring scalability requires robust autoscaling mechanisms and suitable architecture design to handle fluctuating workloads. This paper tackles these challenges by proposing tactics to improve system integration, enhance explainability through metadata and an algorithm process, ensure response consistency via regression testing, and facilitate efficient autoscaling through an event-driven microservice architecture. The evaluation results highlight the effectiveness of these tactics, confirming both functional consistency and robust system performance under varying loads.https://ieeexplore.ieee.org/document/10845786/Artificial intelligenceeducational applicationgenerative AIlarge language modelLLM |
| spellingShingle | Nacha Chondamrongkul Georgi Hristov Punnarumol Temdee Addressing Technical Challenges in Large Language Model-Driven Educational Software System IEEE Access Artificial intelligence educational application generative AI large language model LLM |
| title | Addressing Technical Challenges in Large Language Model-Driven Educational Software System |
| title_full | Addressing Technical Challenges in Large Language Model-Driven Educational Software System |
| title_fullStr | Addressing Technical Challenges in Large Language Model-Driven Educational Software System |
| title_full_unstemmed | Addressing Technical Challenges in Large Language Model-Driven Educational Software System |
| title_short | Addressing Technical Challenges in Large Language Model-Driven Educational Software System |
| title_sort | addressing technical challenges in large language model driven educational software system |
| topic | Artificial intelligence educational application generative AI large language model LLM |
| url | https://ieeexplore.ieee.org/document/10845786/ |
| work_keys_str_mv | AT nachachondamrongkul addressingtechnicalchallengesinlargelanguagemodeldriveneducationalsoftwaresystem AT georgihristov addressingtechnicalchallengesinlargelanguagemodeldriveneducationalsoftwaresystem AT punnarumoltemdee addressingtechnicalchallengesinlargelanguagemodeldriveneducationalsoftwaresystem |