Procedural Knowledge in Pretraining Drives Reasoning in Large Language Models.

Laura Ruis, Maximilian Mozes, Juhan Bae, Siddhartha Rao Kamalakara, Dwaraknath Gnaneshwar, Acyr Locatelli, Robert Kirk, Tim Rocktschel, Edward Grefenstette, Max Bartolo

Browse the full ICLR paper archive.