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.
Guidelines: • The answer [N/A] means that the authors have not reviewed the NeurIPS Code of Ethics
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.