Judging Truncated Answers: DAPO's Overlong Fix
Scoring truncated responses as wrong injects reward noise into the advantage. DAPO either masks their loss or adds a linear penalty ramp before the length cap.
Scoring truncated responses as wrong injects reward noise into the advantage. DAPO either masks their loss or adds a linear penalty ramp before the length cap.
64, 8 or 2 samples per prompt? G is GRPO’s only baseline and its biggest compute knob. What it buys, and why dynamic sampling can stand in for a larger G.
Naive GRPO collapses entropy fast. DAPO’s Clip-Higher only lifts the upper clip bound from 0.2 to 0.28, and the reason is an asymmetry built into PPO-Clip.