EMNLP 2026 Main conference

TDGNet: Hallucination Detection in Diffusion Language Models via Temporal Dynamic Graphs

Arshia Hemmat, Philip Torr, Yongqiang Chen, Junchi Yu

arxiv
Figure from TDGNet: Hallucination Detection in Diffusion Language Models via Temporal Dynamic Graphs

Hallucination in diffusion language models is visible in the denoising trajectory before it reaches the output. TDGNet reads that trajectory as a temporal dynamic graph.

A longer write-up of this work is on its way. Until then the paper and the code are the best place to look.