English

Explaining Modern Gated-Linear RNNs via a Unified Implicit Attention Formulation

Machine Learning 2024-10-21 v2

Abstract

Recent advances in efficient sequence modeling have led to attention-free layers, such as Mamba, RWKV, and various gated RNNs, all featuring sub-quadratic complexity in sequence length and excellent scaling properties, enabling the construction of a new type of foundation models. In this paper, we present a unified view of these models, formulating such layers as implicit causal self-attention layers. The formulation includes most of their sub-components and is not limited to a specific part of the architecture. The framework compares the underlying mechanisms on similar grounds for different layers and provides a direct means for applying explainability methods. Our experiments show that our attention matrices and attribution method outperform an alternative and a more limited formulation that was recently proposed for Mamba. For the other architectures for which our method is the first to provide such a view, our method is effective and competitive in the relevant metrics compared to the results obtained by state-of-the-art Transformer explainability methods. Our code is publicly available.

Keywords

Cite

@article{arxiv.2405.16504,
  title  = {Explaining Modern Gated-Linear RNNs via a Unified Implicit Attention Formulation},
  author = {Itamar Zimerman and Ameen Ali and Lior Wolf},
  journal= {arXiv preprint arXiv:2405.16504},
  year   = {2024}
}
R2 v1 2026-06-28T16:40:42.540Z