Early-Signal Detector

method · first seen 4 Oct 2026

minimax preference optimization

Also: adversarial preference distribution

Formulating alignment as a minimax game where an adversary reweights preferences the policy serves worst.

Mentions per week

0119 May11 Aug10 NovPapersCodeDiscussion

PapersCodeDiscussion

Earliest sources

Latest sources

Mentioned together with

reinforcement learning from human feedbackmulti-objective alignment