Fine-tuning language models on synthetic distribution-sampling prompts improves their ability to generate outputs that match target probability distributions on held-out cases.
Thompson (awarded in 1974)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Probabilistic Calibration Is a Trainable Capability in Language Models
Fine-tuning language models on synthetic distribution-sampling prompts improves their ability to generate outputs that match target probability distributions on held-out cases.