Open access
Jul 2026
Hallucination in Time-series Large Language Models: An empirical lnvestigation and analysis of mitigation strategies.
It is demonstrated that conventional regression metrics alone are insufficient for evaluating time-series LLMs and the need for reliability-focused diagnostics when deploying LLM-based forecasting systems in high-stakes domains is highlighted.
Shamsu Abdullahi, K. U. Danyaro, H. Chiroma et al.
· Scientific Reports · 0 citations