Atlas of Human-AI Interaction: An Interactive Knowledge Graph for Research Sensemaking at Scale

Abstract

The growth and fragmentation of scientific literature make it increasingly difficult for researchers to synthesize findings and build on prior work. This paper presents a framework for organizing empirical findings to support comparison and exploration across papers. The framework combines LLM-powered claim extraction, entity resolution, taxonomy generation, and knowledge graph construction, retaining links to study contexts and sources. An interactive interface supports navigation among constructs and reported relationships, alongside evidence inspection and collection. We instantiate the framework in the Atlas of Human-AI Interaction, organizing 308,802 claims from 31,741 papers. A descriptive corpus analysis and exploratory user study examine how this representation can support research sensemaking and identify opportunities for refinement. The framework and interface offer an initial approach to computational literature synthesis, with potential for adaptation to other empirical domains.