Autoregressive + Chain of Thought $simeq$ Recurrent: Recurrence’s Role in Language Models’ Computability and a Revisit of Recurrent Transformer

View a PDF of the paper titled Autoregressive + Chain of Thought $simeq$ Recurrent: Recurrence’s Role in Language Models’ Computability and a Revisit of Recurrent Transformer, by Xiang Zhang and 2 other authors

View PDF
HTML (experimental)

Abstract:The Transformer architecture excels in a variety of language modeling tasks, outperforming traditional neural architectures such as RNN and LSTM. This is partially due to its elimination of recurrent connections, which allows for parallel training and a smoother flow of gradients. However, this move away from recurrent structures places the Transformer model at the lower end of Chomsky’s computational hierarchy, imposing limitations on its computational abilities. Consequently, even advanced Transformer-based models face considerable difficulties in tasks like counting, string reversal, and multiplication. These tasks, though seemingly elementary, require a level of computational complexity that exceeds the capabilities of the Transformer architecture. Concurrently, the emergence of “Chain of Thought” (CoT) prompting has enabled Transformer-based language models to tackle tasks that were previously impossible or poorly executed. In this work, we thoroughly investigate the influence of recurrent structures in neural models on their reasoning abilities and computability, contrasting the role autoregression plays in the neural models’ computational power. We then shed light on how the CoT approach can mimic recurrent computation and act as a bridge between autoregression and recurrence in the context of language models. It is this approximated recurrence that notably improves the model’s performance and computational capacity. Moreover, we revisit recent recurrent-based Transformer model designs, focusing on their computational abilities through our proposed concept of “recurrence-completeness” and identify key theoretical limitations in models like Linear Transformer and RWKV. Through this, we aim to provide insight into the neural model architectures and prompt better model design.