Abstract:Time series forecasting has become increasingly critical in real-world scenarios, where future sequences are influenced not only by historical patterns but also by forthcoming events. In this context, forecasting must dynamically adapt to complex and stochastic future conditions, which introduces fundamental challenges in both forecasting and evaluation. Traditional methods typically rely on historical data or factual future conditions, while overlooking counterfactual scenarios. Furthermore, many existing approaches are restricted to simple structured conditions, limiting their ability to generalize to the real-world complexities. To address these gaps, we introduce the task of counterfactual time series forecasting with textual conditions, enabling more flexible and condition-aware forecasting. We propose a comprehensive evaluation framework that encompasses both factual and counterfactual settings, even in the absence of ground truth time series. Additionally, we present a novel text-attribution mechanism that distinguishes mutable from immutable factors, thereby improving forecast accuracy under sophisticated and stochastic textual conditions. The project page is at this https URL
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.14422 [cs.LG] |
| (or arXiv:2605.14422v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.14422 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Shuqi Gu [view email]
[v1]
Thu, 14 May 2026 06:10:23 UTC (1,532 KB)