Leveraging In-Context Learning and Retrieval-Augmented Generation for Automatic Question Generation in Educational Domains
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912208669114368 |
|---|---|
| author | Maity, Subhankar Deroy, Aniket Sarkar, Sudeshna |
| author_facet | Maity, Subhankar Deroy, Aniket Sarkar, Sudeshna |
| contents | Question generation in education is a time-consuming and cognitively demanding task, as it requires creating questions that are both contextually relevant and pedagogically sound. Current automated question generation methods often generate questions that are out of context. In this work, we explore advanced techniques for automated question generation in educational contexts, focusing on In-Context Learning (ICL), Retrieval-Augmented Generation (RAG), and a novel Hybrid Model that merges both methods. We implement GPT-4 for ICL using few-shot examples and BART with a retrieval module for RAG. The Hybrid Model combines RAG and ICL to address these issues and improve question quality. Evaluation is conducted using automated metrics, followed by human evaluation metrics. Our results show that both the ICL approach and the Hybrid Model consistently outperform other methods, including baseline models, by generating more contextually accurate and relevant questions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_17397 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Leveraging In-Context Learning and Retrieval-Augmented Generation for Automatic Question Generation in Educational Domains Maity, Subhankar Deroy, Aniket Sarkar, Sudeshna Computation and Language Question generation in education is a time-consuming and cognitively demanding task, as it requires creating questions that are both contextually relevant and pedagogically sound. Current automated question generation methods often generate questions that are out of context. In this work, we explore advanced techniques for automated question generation in educational contexts, focusing on In-Context Learning (ICL), Retrieval-Augmented Generation (RAG), and a novel Hybrid Model that merges both methods. We implement GPT-4 for ICL using few-shot examples and BART with a retrieval module for RAG. The Hybrid Model combines RAG and ICL to address these issues and improve question quality. Evaluation is conducted using automated metrics, followed by human evaluation metrics. Our results show that both the ICL approach and the Hybrid Model consistently outperform other methods, including baseline models, by generating more contextually accurate and relevant questions. |
| title | Leveraging In-Context Learning and Retrieval-Augmented Generation for Automatic Question Generation in Educational Domains |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2501.17397 |