Publikation
Panel on Neural Relational Data: Tabular Foundation Models, LLMs... or both?
Paolo Papotti; Carsten Binnig
In: Proceedings of the VLDB Endowment (PVLDB), Vol. 18, No. 12, Pages 5513-5515, VLDP, 2025.
Zusammenfassung
Recent breakthroughs in artificial intelligence have produced Large
Language Models (LLMs) and a new wave of Tabular Foundation
Models (TFMs). Both promise to redefine how we query, integrate,
and reason over relational data, yet they embody opposing philoso-
phies: LLMs pursue broad generality through massive text-centric
pre-training, whereas TFMs embed inductive biases that mirror
table structure and relational semantics. This panel assembles re-
searchers and practitioners from academia and industry to debate
which path, specialized TFMs, ever stronger general-purpose LLMs,
or a hybrid of the two, will most effectively power the next genera-
tion of data management systems. Panelists will confront questions
of generality, accuracy, scalability, robustness, cost, and usability
across core data management tasks such as Text-to-SQL translation,
schema understanding, and entity resolution. The discussion aims
to surface critical research challenges and guide the community’s
investment of effort and resources over the coming years.