Selective tie learning reduces spurious correlations in preference optimization
Largest predicted reductions are first-order optimal among equal-size tie subsets, and a reward-margin proxy can stand in when influence is costly.
1 stories, newest first · one card per story
Largest predicted reductions are first-order optimal among equal-size tie subsets, and a reward-margin proxy can stand in when influence is costly.
Today 1.5K readers · 2.4K views · 757 reads · all time 189K views