Unveiling Transformers with LEGO: a synthetic reasoning task. (arXiv:2206.04301v2 [cs.LG] UPDATED)

We propose a synthetic task, LEGO (Learning Equality and Group Operations),
that encapsulates the problem of following a chain of reasoning, and we study
how the transformer architectures learn this task. We pay special attention to
data effects such as pretraining (on seemingly unrelated NLP tasks) and dataset
composition (e.g., differing chain length at training and test time), as well
as architectural variants such as weight-tied layers or adding convolutional
components. We study how the trained models eventually succeed at …

arxiv lego lg reasoning transformers