Impact of Causal Structure Integration on TabPFN Performance in Tabular Benchmarks

Synthetic tabular data generation addresses data scarcity and privacy constraints in a variety of domains. Tabular Prior-Data Fitted Network (TabPFN), a recent foundation model for tabular data, has been shown capable of generating high-quality synthetic tabular data. However, TabPFN is autoregressive: features are generated sequentially by conditioning on the previous ones, depending on the order in which they appear in the input data. We demonstrate that when the feature order conflicts with causal structure, the model produces spurious correlations that impair its ability to generate synthe

Research goal: How does integrating causal structure into TabPFN's synthetic data generation affect its performance on downstream task accuracy across different tabular benchmarks compared to standard autoregressive models?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.7/10.