Segment-driven Structural Induction and Semantic Alignment for Heterogeneous Tabular Representation

ArXi:2606.01890v1 Announce Type: new Real-world domains often contain heterogeneous tables whose headers vary while their underlying attribute semantics are shared, making it difficult to induce domain-specialized semantics from table-local evidence alone. Existing encoders model parts of this problem, but often underuse column-level value distributions and apply uniform objectives across attributes with different semantic roles. We propose NAVI, a segment-centric pre