cs.LGNov 11, 2026

From Forecasting to World Modeling: Can Temporal Foundation Models Recover Causal Response?

Authors: Juwon Hong, Minha Hwang, Venkatesh Shankar

Organizations: Seoul National University Seoul, South Korea · Microsoft San Francisco, USA · Cox School of Business Southern Methodist University Dallas, Texas, USA

Abstract

A model that forecasts sales accurately can still mislead a retailer about how sales respond to a price change. We evaluate released tabular and time-series foundation models, as well as a foundation model pretrained specifically to estimate causal effects. We report three findings. First, forecast accuracy does not indicate the accuracy of the predicted effect of price, both on simulated data in which the true effect is known and on real retail sales records. Second, for the tabular foundation models, additional context improves forecasts but not the predicted effect of price. Third, instrumental variables, the standard remedy in econometrics, reduce this error only when supplied in a specific form and increase it for every model under confounding when supplied as raw instruments.

Figures & tables

Appendix figures & tables2 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Does Predictive Performance Translate to Causal Performance? Evaluating tabular foundation models as nuisance learners for causal effect estimation

    Nov 8, 2026Andrew R Weckstein, Issa J Dahabreh, Marinka Zitnik +2Causal Effect EstimationTabular Foundation Models

  2. Causal Analysis for Time Series Foundation Models

    Aug 25, 2026Mathis Jander, Wouter van Heeswijk, Martijn MesTime-Series Foundation ModelsTime Series Modeling