How Do Transformers Learn Topic Structure: Towards a Mechanistic Understanding

Understand

While the successes of transformers across many domains are indisputable, accurate understanding of the learning mechanics is still largely lacking.

• Their capabilities have been probed on benchmarks which include a variety of structured and reasoning tasks -- but mathematical understanding is lagging substantially behind.
• Recent lines of work have begun studying representational aspects of this question: that is, the size/depth/complexity of attention-based networks to perform certain tasks.
• However, there is no guarantee the learning dynamics will converge to the constructions proposed.