A LoRA-based distillation framework transfers Bayesian and prompt-ensemble uncertainty from LLM teachers into single-pass softmax or Dirichlet students, with comparable quality and large speedups.
In: Proceedings of the 41stInternationalConferenceonMachineLearning.ProceedingsofMachineLearn- ing Research, vol
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Toward Efficient Uncertainty in LLMs through Evidential Knowledge Distillation
A LoRA-based distillation framework transfers Bayesian and prompt-ensemble uncertainty from LLM teachers into single-pass softmax or Dirichlet students, with comparable quality and large speedups.