trends.barnas.net

phenomenon · first seen 15 Oct 2026

post-training diversity collapse

Also: behavior sharpening

Reduction in the variety of solutions a language model can produce after reinforcement learning post-training.

Mentions per week

0119 May11 Aug10 NovPapersCodeDiscussion

PapersCodeDiscussion

Earliest sources

Latest sources

Mentioned together with

group relative policy optimizationquality-diversity optimization