Pairwise reference alignment is formulated as an ordinal observable equal to the probability that a model score agrees with reference preferences on triples (x, y+, y-), with centered statistics, margin extensions, estimators, and concentration bounds.
On preference learning based on sequential bayesian optimization with pairwise comparison.arXiv preprint arXiv:2103.13192, 2023
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
-
Pairwise Reference Alignment as a Model-Level Ordinal Observable
Pairwise reference alignment is formulated as an ordinal observable equal to the probability that a model score agrees with reference preferences on triples (x, y+, y-), with centered statistics, margin extensions, estimators, and concentration bounds.