"How Transformers Learn Causal Structure with Gradient Descent."

Eshaan Nichani, Alex Damian, Jason D. Lee (2024)

Details and statistics

DOI: 10.48550/ARXIV.2402.14735

access: open

type: Informal or Other Publication

metadata version: 2024-03-22

a service of  Schloss Dagstuhl - Leibniz Center for Informatics