Beyond Summarization: Designing AI Support for Real-World Expository Writing Tasks
It targets researchers and practitioners in AI and writing support, focusing on real-world expository tasks, but is incremental as it builds on existing work without presenting new empirical results.
The paper addresses the understudied area of AI support for expository writing, such as literature reviews or progress notes, by characterizing it as evidence-based and knowledge-generating, and proposes design components for future research.
Large language models have introduced exciting new opportunities and challenges in designing and developing new AI-assisted writing support tools. Recent work has shown that leveraging this new technology can transform writing in many scenarios such as ideation during creative writing, editing support, and summarization. However, AI-supported expository writing--including real-world tasks like scholars writing literature reviews or doctors writing progress notes--is relatively understudied. In this position paper, we argue that developing AI supports for expository writing has unique and exciting research challenges and can lead to high real-world impacts. We characterize expository writing as evidence-based and knowledge-generating: it contains summaries of external documents as well as new information or knowledge. It can be seen as the product of authors' sensemaking process over a set of source documents, and the interplay between reading, reflection, and writing opens up new opportunities for designing AI support. We sketch three components for AI support design and discuss considerations for future research.