AI RESEARCH

HIVE: Hidden-Evidence Verification for Hallucination Detection in Diffusion Large Language Models

arXiv CS.CL

ArXi:2604.26139v1 Announce Type: new Diffusion large language models generate text through multi-step denoising, where hallucination signals may emerge throughout the trajectory rather than only in the final output. Existing detectors mainly rely on output uncertainty or coarse trace statistics, which often fail to capture the richer hidden dynamics of D-LLMs.