Ensemble learning with RAG model to reduce redundant question topics in auto-generated exam questions
Abstract Reducing redundant question topics during automatic question generation (AQG) is essential for enhancing the quality of test sheets in assessment. Existing AQG models frequently generate repetitive questions due to insufficient named entity (Question Topic) diversity. This study aims to red...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2025-08-01
|
| Series: | Discover Computing |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s10791-025-09683-2 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849234567485980672 |
|---|---|
| author | R. Tharaniya Sairaj S. R. Balasundaram |
| author_facet | R. Tharaniya Sairaj S. R. Balasundaram |
| author_sort | R. Tharaniya Sairaj |
| collection | DOAJ |
| description | Abstract Reducing redundant question topics during automatic question generation (AQG) is essential for enhancing the quality of test sheets in assessment. Existing AQG models frequently generate repetitive questions due to insufficient named entity (Question Topic) diversity. This study aims to reduce redundancy in auto generated questions by improving diversity in question topics. The methodology is organised in three main phases: first, a fuzzy ontology mapping technique with ensemble learning is applied to generate expanded entity-relationship set generation from external Knowledge Graphs. Second, the generated entity-relationship set is integrated with Retrieval Augmented Generation (RAG) model for source text expansion via augmentation. Third, T5-shd, a pretrained AQG model is adopted to reduce repetition in generated questions. Comparison against baselines such as T5-e2e and T5-ppl shows substantial performance gain as well as reduction in redundancy. Experimental results on various datasets show that the proposed RAG + T5 model reduces redundant question topics along with an improvement in terms of ROUGE-2 metric (up to 5%) and BERTScore (up to 12%) over existing methods. The application of Ensemble Pruning, specifically with the m-EPIC algorithm, further enhances accuracy while reducing computational overhead (around 26%). These findings highlight the efficacy of combining ensemble learning with RAG-based transformers to refine AQG, ensuring improved question diversity and balanced relevance of generated questions. Additionally, this approach helps to reduce model complexity in Automatic Question Generation. |
| format | Article |
| id | doaj-art-d3540d99962a4e7aa0c6f126fc589262 |
| institution | Kabale University |
| issn | 2948-2992 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Springer |
| record_format | Article |
| series | Discover Computing |
| spelling | doaj-art-d3540d99962a4e7aa0c6f126fc5892622025-08-20T04:03:06ZengSpringerDiscover Computing2948-29922025-08-0128111710.1007/s10791-025-09683-2Ensemble learning with RAG model to reduce redundant question topics in auto-generated exam questionsR. Tharaniya Sairaj0S. R. Balasundaram1Department of Computer Science Engineering, Indian Institute of Information TechnologyDepartment of Computer Applications, National Institute of TechnologyAbstract Reducing redundant question topics during automatic question generation (AQG) is essential for enhancing the quality of test sheets in assessment. Existing AQG models frequently generate repetitive questions due to insufficient named entity (Question Topic) diversity. This study aims to reduce redundancy in auto generated questions by improving diversity in question topics. The methodology is organised in three main phases: first, a fuzzy ontology mapping technique with ensemble learning is applied to generate expanded entity-relationship set generation from external Knowledge Graphs. Second, the generated entity-relationship set is integrated with Retrieval Augmented Generation (RAG) model for source text expansion via augmentation. Third, T5-shd, a pretrained AQG model is adopted to reduce repetition in generated questions. Comparison against baselines such as T5-e2e and T5-ppl shows substantial performance gain as well as reduction in redundancy. Experimental results on various datasets show that the proposed RAG + T5 model reduces redundant question topics along with an improvement in terms of ROUGE-2 metric (up to 5%) and BERTScore (up to 12%) over existing methods. The application of Ensemble Pruning, specifically with the m-EPIC algorithm, further enhances accuracy while reducing computational overhead (around 26%). These findings highlight the efficacy of combining ensemble learning with RAG-based transformers to refine AQG, ensuring improved question diversity and balanced relevance of generated questions. Additionally, this approach helps to reduce model complexity in Automatic Question Generation.https://doi.org/10.1007/s10791-025-09683-2Named entity selectionEnsemble pruning algorithmKnowledge graphsRetrieval augmented generationAutomatic question generation. |
| spellingShingle | R. Tharaniya Sairaj S. R. Balasundaram Ensemble learning with RAG model to reduce redundant question topics in auto-generated exam questions Discover Computing Named entity selection Ensemble pruning algorithm Knowledge graphs Retrieval augmented generation Automatic question generation. |
| title | Ensemble learning with RAG model to reduce redundant question topics in auto-generated exam questions |
| title_full | Ensemble learning with RAG model to reduce redundant question topics in auto-generated exam questions |
| title_fullStr | Ensemble learning with RAG model to reduce redundant question topics in auto-generated exam questions |
| title_full_unstemmed | Ensemble learning with RAG model to reduce redundant question topics in auto-generated exam questions |
| title_short | Ensemble learning with RAG model to reduce redundant question topics in auto-generated exam questions |
| title_sort | ensemble learning with rag model to reduce redundant question topics in auto generated exam questions |
| topic | Named entity selection Ensemble pruning algorithm Knowledge graphs Retrieval augmented generation Automatic question generation. |
| url | https://doi.org/10.1007/s10791-025-09683-2 |
| work_keys_str_mv | AT rtharaniyasairaj ensemblelearningwithragmodeltoreduceredundantquestiontopicsinautogeneratedexamquestions AT srbalasundaram ensemblelearningwithragmodeltoreduceredundantquestiontopicsinautogeneratedexamquestions |