AI RESEARCH
TabReX : Tabular Referenceless eXplainable Evaluation
arXiv CS.CL
•
ArXi:2512.15907v2 Announce Type: replace Evaluating the quality of tables generated by large language models (LLMs) remains an open challenge: existing metrics either flatten tables into text, ignoring structure, or rely on fixed references that limit generalization. We present TabReX, a reference-less, property-driven framework for evaluating tabular generation via graph-based reasoning.