How to Improve the Explanatory Power of an Intelligent Textbook: a Case Study in Legal Writing

• Published in: International journal of artificial intelligence in education
• Main Authors: Sovrano, Francesco, Ashley, Kevin, Brusilovsky, Peter Leonid, Vitali, Fabio
• Format: Journal Article
• Language: English
• Published: 06.05.2024
• ISSN: 1560-4292; 1560-4306
• DOI: 10.1007/s40593-024-00399-w

Explanatory processes are at the core of scientific investigation, legal reasoning, and education. However, effectively explaining complex or large amounts of information, such as that contained in a textbook or library, in an intuitive, user-centered way is still an open challenge. Indeed, different people may search for and request different types of information, even though texts typically have a predefined exposition and content. With this paper, we investigate how explanatory AI can better exploit the full potential of the vast and rich content library at our disposal. Based on a recent theory of explanations from Ordinary Language Philosophy, which frames the explanation process as illocutionary question-answering, we have developed a new type of interactive and adaptive textbook. Using the latest question-answering technology, our e-book software (YAI4Edu, for short) generates on-demand, expandable explanations that can help readers effectively explore teaching materials in a pedagogically productive way. It does this by extracting a specialized knowledge graph from a collection of books or other resources that helps identify the most relevant questions to be answered for a satisfactory explanation. We tested our technology with excerpts from a textbook that teaches how to write legal memoranda in the U.S. legal system. Then, to see whether YAI4Edu-enhanced textbooks are better than random and existing, general-purpose explanatory tools, we conducted a within-subjects user study with more than 100 English-speaking students. The students rated YAI4Edu’s explanations the highest. According to the students, the explanatory content generated by YAI4Edu is, on average, statistically better than two baseline alternatives ( P values below .005).