Response times modeled as drift-diffusion processes enable consistent estimation of population-average preferences from heterogeneous anonymous binary choices.
Yu Meng, Mengzhou Xia, and Danqi Chen
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
fields
cs.LG 4verdicts
UNVERDICTED 4representative citing papers
A threshold-guided alignment method lets visual generative models be optimized directly from scalar human ratings instead of requiring paired preference data.
A controlled unification of direct alignment algorithms shows the ranking objective (pairwise vs pointwise) drives alignment quality more than the scalar score optimized.
UNA unifies binary, pairwise, and score-based feedback for LLM alignment via a generalized implicit reward function shown optimal by the log sum inequality.
citing papers explorer
-
Response Time Enhances Alignment with Heterogeneous Preferences
Response times modeled as drift-diffusion processes enable consistent estimation of population-average preferences from heterogeneous anonymous binary choices.
-
Threshold-Guided Optimization for Visual Generative Models
A threshold-guided alignment method lets visual generative models be optimized directly from scalar human ratings instead of requiring paired preference data.
-
The Differences Between Direct Alignment Algorithms are a Blur
A controlled unification of direct alignment algorithms shows the ranking objective (pairwise vs pointwise) drives alignment quality more than the scalar score optimized.
-
UNA: A Unified Supervised Framework for Efficient LLM Alignment Across Feedback Types
UNA unifies binary, pairwise, and score-based feedback for LLM alignment via a generalized implicit reward function shown optimal by the log sum inequality.