Generating Multiple-Choice Knowledge Questions with Interpretable Difficulty Estimation using Knowledge Graphs and Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Şakiroğlu, Mehmet Can, Güvenir, H. Altay, Kaya, Kamer
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917401642139648
author Şakiroğlu, Mehmet Can
Güvenir, H. Altay
Kaya, Kamer
author_facet Şakiroğlu, Mehmet Can
Güvenir, H. Altay
Kaya, Kamer
contents Generating multiple-choice questions (MCQs) with difficulty estimation remains challenging in automated MCQ-generation systems used in adaptive, AI-assisted education. This study proposes a novel methodology for generating MCQs with difficulty estimation from the input documents by utilizing knowledge graphs (KGs) and large language models (LLMs). Our approach uses an LLM to construct a KG from input documents, from which MCQs are then systematically generated. Each MCQ is generated by selecting a node from the KG as the key, sampling a related triple or quintuple -- optionally augmented with an extra triple -- and prompting an LLM to generate a corresponding stem from these graph components. Distractors are then selected from the KG. For each MCQ, nine difficulty signals are computed and combined into a unified difficulty score using a data-driven approach. Experimental results demonstrate that our method generates high-quality MCQs whose difficulty estimation is interpretable and aligns with human perceptions. Our approach improves automated MCQ generation by integrating structured knowledge representations with LLMs and a data-driven difficulty estimation model.
format Preprint
id arxiv_https___arxiv_org_abs_2604_10748
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Generating Multiple-Choice Knowledge Questions with Interpretable Difficulty Estimation using Knowledge Graphs and Large Language Models
Şakiroğlu, Mehmet Can
Güvenir, H. Altay
Kaya, Kamer
Computation and Language
Artificial Intelligence
Machine Learning
Generating multiple-choice questions (MCQs) with difficulty estimation remains challenging in automated MCQ-generation systems used in adaptive, AI-assisted education. This study proposes a novel methodology for generating MCQs with difficulty estimation from the input documents by utilizing knowledge graphs (KGs) and large language models (LLMs). Our approach uses an LLM to construct a KG from input documents, from which MCQs are then systematically generated. Each MCQ is generated by selecting a node from the KG as the key, sampling a related triple or quintuple -- optionally augmented with an extra triple -- and prompting an LLM to generate a corresponding stem from these graph components. Distractors are then selected from the KG. For each MCQ, nine difficulty signals are computed and combined into a unified difficulty score using a data-driven approach. Experimental results demonstrate that our method generates high-quality MCQs whose difficulty estimation is interpretable and aligns with human perceptions. Our approach improves automated MCQ generation by integrating structured knowledge representations with LLMs and a data-driven difficulty estimation model.
title Generating Multiple-Choice Knowledge Questions with Interpretable Difficulty Estimation using Knowledge Graphs and Large Language Models
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2604.10748