DynHD: Hallucination Detection for Diffusion Large Language Models via Denoising Dynamics Deviation Learning

ArXi:2603.16459v1 Announce Type: new Diffusion large language models (D-LLMs) have emerged as a promising alternative to auto-regressive models due to their iterative refinement capabilities. However, hallucinations remain a critical issue that hinders their reliability. To detect hallucination responses from model outputs, token-level uncertainty (e.g., entropy) has been widely used as an effective signal to indicate potential factual errors.