Score: 0

Mitigating Exposure Bias in Risk-Aware Time Series Forecasting with Soft Tokens

Published: December 10, 2025 | arXiv ID: 2512.10056v1

By: Alireza Namazi, Amirreza Dolatpour Fathkouhi, Heman Shakeri

Potential Business Impact:

Helps doctors predict health problems better.

Business Areas:
Predictive Analytics Artificial Intelligence, Data and Analytics, Software

Autoregressive forecasting is central to predictive control in diabetes and hemodynamic management, where different operating zones carry different clinical risks. Standard models trained with teacher forcing suffer from exposure bias, yielding unstable multi-step forecasts for closed-loop use. We introduce Soft-Token Trajectory Forecasting (SoTra), which propagates continuous probability distributions (``soft tokens'') to mitigate exposure bias and learn calibrated, uncertainty-aware trajectories. A risk-aware decoding module then minimizes expected clinical harm. In glucose forecasting, SoTra reduces average zone-based risk by 18\%; in blood-pressure forecasting, it lowers effective clinical risk by approximately 15\%. These improvements support its use in safety-critical predictive control.

Country of Origin
🇺🇸 United States

Page Count
8 pages

Category
Computer Science:
Machine Learning (CS)