DARC is a retraining-free inference-time method that frames response selection as distributionally robust optimization to reduce disagreement and tail risk under heterogeneous preferences.
It answers directly by grounding the issue in the U.S
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
DARC: Disagreement-Aware Alignment via Risk-Constrained Decoding
DARC is a retraining-free inference-time method that frames response selection as distributionally robust optimization to reduce disagreement and tail risk under heterogeneous preferences.