Urgent.News

What's breaking now, across thousands of outlets.

AI

Base Models Can Reason By Taking a Cue From Training Data

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…

We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.

Read the original at arxiv.org →

More in AI

More from Monday 5 October →