trends.barnas.net

method · first seen 13 Oct 2026

preference learning

Also: pairwise comparison, preference comparisons, pairwise preference learning, reward learning from human feedback

Training models from human or simulated pairwise comparisons of outputs.

Mentions per week

0519 May11 Aug10 NovPapersCodeDiscussion

PapersCodeDiscussion

Earliest sources

Latest sources

Mentioned together with

pluralistic alignmentGaussian processBayesian optimizationprivileged information distillationadaptive evaluation allocationhuman-in-the-loop