Multi-head Transformers Provably Learn Symbolic Multi-step Reasoning via Gradient Descent

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Tong, Huang, Yu, Liang, Yingbin, Chi, Yuejie
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!