SOURCE-LINKED INTELLIGENCE

EviMap: Evidence-Grounded Hierarchical Topic Maps for Exploring Unlabeled Corpora

arXiv · AI, language, vision and robotics · article · Sep 6, 2026 · UTC

Research teams and organizations often explore unfamiliar free-text collections, from survey comments and reviews to reports and domain documents, before labels, queries or coding schemes exist. At this stage, the first thematic map shapes what users notice, prioritize and carry into downstream analysis, so it should be trusted only insofar as it can be verified. Existing options force a trade-off between scale and verifiability. Qualitative coding preserves evidence but is slow. Search presupposes a query. Clustering and topic models scale but produce labels users must interpret. One-shot lar

Read original source ↗ Open in workspace

recordType

paper

region

Global