LoID pulls informative priors directly from LLM token predictions instead of generated text, recovering up to 59% of the oracle performance gap on 10 OOD tabular datasets.
Uniform priors violate this structure, treating β= 0.1 and β= 4.9 as equally plausible a prior
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
-
What Language Models Know But Don't Say: Non-Generative Prior Extraction for Generalization
LoID pulls informative priors directly from LLM token predictions instead of generated text, recovering up to 59% of the oracle performance gap on 10 OOD tabular datasets.