Turning citation networks inside out: Studying science using content-based knowledge graphs from LLM-derived taxonomies
Seorin Kim, Vincent Holst, Vincent Ginis · Quantitative Science Studies · 2026
Abstract Scientific fields are often mapped using citations and metadata, even though knowledge is transmitted primarily through content. We introduce an “inside-out” approach that reconstructs field structure directly from text by representing each paper as a small set of interpretable knowledge components. Using a large language model to induce domain-specific taxonomies and label papers, each publication is encoded as a triplet of measure, data type, and research question type. These triplets define a knowledge graph whose edges are weighted by the number of shared papers. Applied to 617 studies on intergenerational wealth mobility, the graph reveals a stable methodological backbone centered on regression-based mobility measures, alongside substantial temporal variation in the recombination of components. We further utilize normalized betweenness-to-connectivity ratios to identify components and pairings that act as structural bridges disproportionate to their prevalence. This content-derived, taxonomy-driven mapping complements citation-based approaches by exposing the evolving architecture of methods, data, and questions that define a field.