Forecasting Time Series Responses to Counterfactual Exogenous Event Descriptions

Real-world time series respond to external events. Prior work shows that exogenous-event text can improve factual forecasts, while counterfactual modeling has been studied for structured interventions and target-derived or target-descriptive text. Yet whether a model produces the appropriate numerical response when the same history is paired with a different free-form exogenous event remains unclear. We propose $\text{MEETS}$, a conditional diffusion model with factorized history-event conditioning and matched conditioning-swap objectives that encourage use of both sources. Across traffic, energy, and treatment-response domains, $\text{MEETS}$ lowers factual forecasting error and improves counterfactual event-specific responses, including direction and magnitude, while generalizing to unseen event configurations.