Enhancing Text Comprehension forLanguage Learning by GeneratingQuestions with Eye-Tracking and LLM

要約

This paper presents a system that supports a reader by identifying difficult paragraphs using eye-tracking implicitly and generating compre- hension questions with a Large Language Model (LLM). Our aim is to evaluate the potential of generative AI as a tool to augment human cog- gnitive capabilities. If readers answer the questions correctly, this confirms that they understand the text. Conversely, if they answer incorrectly, it indicates a lack of understanding, allowing the system to provide explana- tions for the misunderstood parts, thereby improving the readers’ under- standing of the text. Our experiment showed that half of the participants improved their comprehension of the text. Further analysis revealed that the motivation to read/use system is one of the most important factor to increase the effectiveness of the proposed system.