Selenite: Scaffolding Online Sensemaking with Comprehensive Overviews Elicited from Large Language Models
This addresses the cold-start problem in sensemaking tools for users needing to navigate unfamiliar information, though it appears incremental by applying LLMs to an existing bottleneck.
The paper tackled the challenge of sensemaking in unfamiliar domains by introducing Selenite, a system that uses Large Language Models to automatically generate comprehensive overviews of options and criteria, which significantly accelerated users' information processing and improved their comprehension and sensemaking experience.
Sensemaking in unfamiliar domains can be challenging, demanding considerable user effort to compare different options with respect to various criteria. Prior research and our formative study found that people would benefit from reading an overview of an information space upfront, including the criteria others previously found useful. However, existing sensemaking tools struggle with the "cold-start" problem -- it not only requires significant input from previous users to generate and share these overviews, but such overviews may also turn out to be biased and incomplete. In this work, we introduce a novel system, Selenite, which leverages Large Language Models (LLMs) as reasoning machines and knowledge retrievers to automatically produce a comprehensive overview of options and criteria to jumpstart users' sensemaking processes. Subsequently, Selenite also adapts as people use it, helping users find, read, and navigate unfamiliar information in a systematic yet personalized manner. Through three studies, we found that Selenite produced accurate and high-quality overviews reliably, significantly accelerated users' information processing, and effectively improved their overall comprehension and sensemaking experience.