Preprint
Jul 2026
DeMTS: Denoising Trajectories as Multivariate Time Series for Hallucination Detection in Diffusion Language Models
A D-LLM hallucination detection framework that formulates the Denoising trajectories as Multivariate Time Series over learnable latent variables (DeMTS for short) that outperforms existing hallucination detection methods while maintaining strong robustness, efficiency, and cross-task transferability.
Xin Zhang, Yili Wang, Yue Tan et al.
· 0 citations