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

arXiv cs.CL / 4/14/2026

💬 OpinionIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper presents a methodology to generate multiple-choice questions (MCQs) from input documents while also estimating each question’s difficulty.
It uses a large language model (LLM) to build a knowledge graph (KG) from the documents, then generates MCQs by selecting KG nodes, sampling related triples/quintuples, and prompting an LLM to draft the MCQ stem.
Distractors are chosen from the same knowledge graph, tying both correctness options and question formulation to the structured representation.
For difficulty estimation, the method computes nine separate difficulty signals and combines them into a single unified, data-driven score.
Experiments indicate the generated MCQs are high quality and that the difficulty estimates are interpretable and consistent with human judgments, improving automated MCQ generation for adaptive education.

Abstract

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.