On Few-Shot Prompting for Controllable Question-Answer Generation in Narrative Comprehension
This work addresses controllable question generation for narrative comprehension, particularly for children's education, but it is incremental as it builds on existing prompting methods.
The study tackled controllable question-answer generation from children's narrative texts by proposing a few-shot prompting strategy to control attributes like explicitness and narrative elements, showing effectiveness with improvements in semantic closeness and diversity but not always statistically significant.
Question Generation aims to automatically generate questions based on a given input provided as context. A controllable question generation scheme focuses on generating questions with specific attributes, allowing better control. In this study, we propose a few-shot prompting strategy for controlling the generation of question-answer pairs from children's narrative texts. We aim to control two attributes: the question's explicitness and underlying narrative elements. With empirical evaluation, we show the effectiveness of controlling the generation process by employing few-shot prompting side by side with a reference model. Our experiments highlight instances where the few-shot strategy surpasses the reference model, particularly in scenarios such as semantic closeness evaluation and the diversity and coherency of question-answer pairs. However, these improvements are not always statistically significant. The code is publicly available at github.com/bernardoleite/few-shot-prompting-qg-control.