一作ACL 2026Findings· Findings of ACL
Lost in Diffusion: Uncovering Hallucination Patterns and Failure Modes in Diffusion Large Language Models
Zhengnan Guo · Fei Tan
摘要
While Diffusion Large Language Models (dLLMs) have emerged as a promising non-autoregressive paradigm comparable to auto-regressive (AR) models, their faithfulness, specifically regarding hallucination, remains largely underexplored. To bridge this gap, we present the first controlled comparative...