.png){kind=icon}
.png){kind=icon}
Return
Knowledge Representation Approaches for Educational Question Generation
.png){kind=icon}
PRE
AI
DOI：10.1007/978-3-032-02551-7_20.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Teachers are increasingly using prompted LLMs to generate exam questions, and students can use generated questions for self-assessment. When generating questions from a given educational text-rather than relying solely on the LLM's internal knowledge-handling long textual content, such as a textbook spanning hundreds of pages, presents a challenge. In this paper, we experiment with three knowledge representation approaches tailored for educational question generation using LLMs. As a novel contribution among these alternatives, we adapt the atomic fact decomposition method from fact-checking research to the educational domain. We manually evaluate the generated questions based on various criteria. Our empirical results indicate that a list of atomic facts provides a better foundation for question generation than long plain text and that LLM-based question generation from Knowledge Graph triplets outperforms rule-based question generation from Knowledge Graphs.
Keywords:
Knowledge Representation
Educational Question Generation
Atomic Fact Decomposition
Large Language Models
Knowledge Graphs
Journal
T
IF:
0
Papers:
23
Citations:
0