Multimodal Tabular Foundation Models Outperform Unimodal Models Under Adversarial Noise on TabMNAR

Abstract

Abstract: This report synthesises findings from 13 peer-reviewed papers addressing the following research question: How do multimodal tabular foundation models (e.g., integrating text and numerical data) perform compared to unimodal models on TabMNAR with adversarial noise, measured by robust accuracy and fairness. 0 claims were extracted from source literature; 0 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 3.3/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research Question

How do multimodal tabular foundation models (e.g., integrating text and numerical data) perform compared to unimodal models on TabMNAR with adversarial noise, measured by robust accuracy and fairness across different noise distributions?

Verification Level

Descriptive public verification status only; aggregate claim counts are public, but individual claim records are not exposed here.

Quality Tier

Descriptive public triage only; this tier does not alter current publication or DOI behavior.

Quality Dimensions

Automated triage signals derived from public fields; not human peer review or independent validation.

Correction Record

Public corrections are additive records. Current status does not claim the synthesis is error-free.

Provenance