Foundation models for natural language processing have many coherent definitions of hallucination and methods for its detection and mitigation. However, analogous definitions and methods do not exist for multi-variate time-series (MVTS) foundation models. We propose new definitions for MVTS hallucination, along with new detection and mitigation methods using a diffusion model to estimate hallucination levels. We derive relational datasets from popular time-series datasets to benchmark these relational hallucination levels. Using these definitions and models, we find that open-source pre-trained MVTS imputation foundation models relationally hallucinate on average up to 59.5% as much as a weak baseline. The proposed mitigation method reduces this by up to 47.7% for these models. The definition and methods may improve adoption and safe usage of MVTS foundation models.
@article{arxiv.2508.00881,
title = {Hallucination Detection and Mitigation with Diffusion in Multi-Variate Time-Series Foundation Models},
author = {Vijja Wichitwechkarn and Charles Fox and Ruchi Choudhary},
journal= {arXiv preprint arXiv:2508.00881},
year = {2025}
}