Advancing Question Generation with Joint Narrative and Difficulty Control

2025-06-07

AI Summary

Existing question generation (QG) research lacks joint control over question difficulty and narrativity—two interdependent attributes critical for educational reading comprehension tasks. Method: We propose the first narrativity–difficulty jointly controllable QG framework, overcoming the limitations of single-attribute control. Grounded in controllable text generation, our approach integrates prompt engineering, attribute-decoupled representation learning, and conditional decoding to explicitly model the interaction and trade-offs between these dimensions. Contribution/Results: Experiments demonstrate that our method significantly improves control precision over both difficulty and narrativity while preserving question quality. Evaluation on learner-level adaptation and pedagogical context alignment confirms its effectiveness and practical utility in educational QG applications.

Technology Category

• Natural Language Processing: Question Answering
• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Cognitive Modeling & Cognitive Systems: Computational Creativity

Application Category

• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Community question answering

Abstract

Question Generation (QG), the task of automatically generating questions from a source input, has seen significant progress in recent years. Difficulty-controllable QG (DCQG) enables control over the difficulty level of generated questions while considering the learner's ability. Additionally, narrative-controllable QG (NCQG) allows control over the narrative aspects embedded in the questions. However, research in QG lacks a focus on combining these two types of control, which is important for generating questions tailored to educational purposes. To address this gap, we propose a strategy for Joint Narrative and Difficulty Control, enabling simultaneous control over these two attributes in the generation of reading comprehension questions. Our evaluation provides preliminary evidence that this approach is feasible, though it is not effective across all instances. Our findings highlight the conditions under which the strategy performs well and discuss the trade-offs associated with its application.

Problem

• Combining narrative and difficulty control in question generation
• Generating educationally tailored reading comprehension questions
• Evaluating feasibility and trade-offs of joint control strategy

Innovation

• Joint control over narrative and difficulty
• Generates tailored educational questions
• Evaluates feasibility and performance conditions