A Design Space for the Critical Validation of LLM-Generated Tabular Data
| dc.contributor.author | Sachdeva, Madhav | en_US |
| dc.contributor.author | Narayanan, Christopher | en_US |
| dc.contributor.author | Wiedenkeller, Marvin | en_US |
| dc.contributor.author | Sedlakova, Jana | en_US |
| dc.contributor.author | Bernard, Jürgen | en_US |
| dc.contributor.editor | Schulz, Hans-Jörg | en_US |
| dc.contributor.editor | Villanova, Anna | en_US |
| dc.date.accessioned | 2025-05-26T06:30:42Z | |
| dc.date.available | 2025-05-26T06:30:42Z | |
| dc.date.issued | 2025 | |
| dc.description.abstract | LLM-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. | en_US |
| dc.description.sectionheaders | Best Paper | |
| dc.description.seriesinformation | EuroVis Workshop on Visual Analytics (EuroVA) | |
| dc.identifier.doi | 10.2312/eurova.20251101 | |
| dc.identifier.isbn | 978-3-03868-283-7 | |
| dc.identifier.issn | 2664-4487 | |
| dc.identifier.pages | 6 pages | |
| dc.identifier.uri | https://doi.org/10.2312/eurova.20251101 | |
| dc.identifier.uri | https://diglib.eg.org/handle/10.2312/eurova20251101 | |
| dc.publisher | The Eurographics Association | en_US |
| dc.rights | Attribution 4.0 International License | |
| dc.rights.uri | https://creativecommons.org/licenses/by/4.0/ | |
| dc.title | A Design Space for the Critical Validation of LLM-Generated Tabular Data | en_US |