Granuscore: A Reference-Free Measure of Granularity for Text Analysis and Question Answering
For researchers in text analysis and NLP, Granuscore provides a principled, reference-free measure of granularity that captures structural properties beyond surface-level metrics.
Granuscore is a reference-free measure of text granularity that leverages hierarchical embedding spaces. It reliably recovers hierarchical orderings on the Granola-EQ dataset, explains non-linear variation in sentence specificity beyond length, and reveals consistent granularity differences in QA benchmarks, positioning it as a scalable tool for granularity analysis.
Natural language conveys information at varying levels of granularity, from fine-grained references to broad descriptions. While granularity is fundamental to human communication, existing measures mostly capture surface detail or sentence specificity. We introduce Granuscore, a reference-free measure of granularity that leverages structural properties of a hierarchical embedding space. Granuscore reliably recovers hierarchical orderings on the Granola-EQ dataset and captures expected differences in granularity across discourse contexts. Across domains, we further show that Granuscore explains non-linear variation in sentence specificity beyond sentence length. Finally, we apply Granuscore to four question-answering benchmarks and analyze how granularity differs for questions, gold answers, and model outputs across response outcomes. The analysis reveals consistent differences in model behavior and provides a principled lens for characterizing the difficulty of QA datasets. Together, the results position Granuscore as a scalable, broadly applicable tool for analyzing granularity in text.