同时控制问题叙事和难度，让生成的阅读理解题更贴合教学需求。
Advancing Question Generation with Joint Narrative and Difficulty Control
- 联合建模叙事风格与难度等级，实现双控生成。
- 在特定条件下有效提升题目适配性，但非全场景适用。
- 适合教育AI、智能出题系统开发者参考。
问题生成（QG）近年来发展迅速。难度可控的QG（DCQG）能根据学习者能力调整问题难度，而叙事可控的QG（NCQG）则可调控问题中的叙事特征。然而，现有研究缺乏对这两种控制机制的融合，限制了其在教育场景中的应用。为此，本文提出一种联合叙事与难度控制的策略，实现阅读理解题生成中双重属性的同步调控。评估结果显示该方法具备可行性，但在部分实例中表现不佳。研究揭示了其有效条件，并讨论了实际应用中的权衡因素。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。