Paper recorded by Signals 4 on 2026-10-05 in cs.AI. Abstract reproduced from arXiv; link to the original below.
Published 2026-10-05 on arXiv · recorded by Signals 4 on 2026-10-06
Category: cs.AI · 人工智能 · first seen 2026-10-06
A language model can give a correct answer more probability than any single incorrect answer and still usually sample an incorrect one, because the incorrect answers together hold more probability. The power distribution raises each complete answer's probability to a power above one and renormalizes, shifting probability toward answers the model finds most likely (sharpening). Sampling from it imp