Minglai Yang
@Yminglai
๊ฐ์
May 2024
196 ํ๋ก์ ์ค 325 ํฌ
RL against rubrics quietly reward-hacks: the training judge keeps scoring higher while true quality falls.
One-line fix: randomly drop part of the rubric each step, so the policy never optimize the same set of rubrics twice.
๐
๋ ๋ณด๊ธฐ
