Uncertainty signals from LLDM denoising trajectories, including a proven lower bound on the training objective, achieve near sampling-based hallucination detection at up to 100x lower cost.
To further demonstrate the robustness of our findings, we conducted experiments across two LLMs and eight datasets from diverse domains and tasks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Uncertainty Quantification for Large Language Diffusion Models
Uncertainty signals from LLDM denoising trajectories, including a proven lower bound on the training objective, achieve near sampling-based hallucination detection at up to 100x lower cost.