Procedural Knowledge in Pretraining Drives Reasoning in LLMs
Free while signed in. Answers cite the passages they came from.
First page

The curator’s take
studies what documents in the pertaining influence model outputs; by looking at the pertaining data, it tries to understand better what kind of generalization strategies LLMs use to perform reasoning tasks; when performing reasoning tasks, it finds that influential documents contain procedural knowledge (e.g., demonstrating how to obtain a solution using formulae or code).
Every Monday
Get next week’s papers.
The same picks and the same summaries, in your inbox. Free, and 176 issues deep.
Subscribe on Substack