AI RESEARCH
Lost in Diffusion: Uncovering Hallucination Patterns and Failure Modes in Diffusion Large Language Models
arXiv CS.CL
•
ArXi:2604.10556v1 Announce Type: new While Diffusion Large Language Models (dLLMs) have emerged as a promising non-autoregressive paradigm comparable to autoregressive (AR) models, their faithfulness, specifically regarding hallucination, remains largely underexplored. To bridge this gap, we present the first controlled comparative study to evaluate hallucination patterns in dLLMs. Our results nstrate that current dLLMs exhibit a higher propensity for hallucination than AR counterparts controlled for architecture, scale, and pre.