Sachdeva, MadhavNarayanan, ChristopherWiedenkeller, MarvinSedlakova, JanaBernard, JürgenSchulz, Hans-JörgVillanova, Anna2025-05-262025-05-262025978-3-03868-283-72664-4487https://doi.org/10.2312/eurova.20251101https://diglib.eg.org/handle/10.2312/eurova20251101LLM-generated tabular data is creating new opportunities for data-driven applications in academia, business, and society. To leverage benefits like missing value imputation, labeling, and enrichment with context-aware attributes, LLM-generated data needs a critical validation process. The number of pioneering approaches is increasing fast, opening a promising validation space that, so far, remains unstructured. We present a design space for the critical validation of LLM-generated tabular data with two dimensions: First, the Analysis Granularity dimension-from within-attribute (single-item and multi-item) to acrossattribute perspectives (1×1, 1×m, and n×n). Second, the Data Source dimension-differentiating between LLM-generated values, ground truth values, explanations, and their combinations. We discuss analysis tasks for each dimension cross-cut, map 19 existing validation approaches, and discuss the characteristics of two approaches in detail, demonstrating descriptive power.Attribution 4.0 International License10.2312/eurova.202511016 pages