Selenite: Scaffolding Online Sensemaking with Comprehensive Overviews Elicited from Large Language Models

TL;DR

Selenite is a system that uses large language models to automatically generate comprehensive overviews for sensemaking, addressing the cold-start problem and enhancing user understanding in unfamiliar domains.

Contribution

This work introduces Selenite, a novel LLM-based system that automatically creates and adapts overviews to facilitate sensemaking, overcoming limitations of existing tools.

Findings

Selenite produces accurate, high-quality overviews reliably.

It significantly accelerates users' information processing.

It improves overall comprehension and sensemaking experience.

Abstract

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.