Base Models Can Reason By Taking a Cue From Training Data

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

Abstract

In this paper, we study how training data creates associations between the tokens at the start of a base model's response and the reasoning behavior that follows. First, we demonstrate that fixing particular starting token cues makes a base model's performance competitive with that of its reinforcement learning (RL)-trained counterparts on math and coding. For instance, the cue ".\n\nOkay" raises

Read on arXiv →