Attention Meets Post-hoc Interpretability: A Mathematical Perspective
Attention-based architectures, in particular transformers, are at the heart of a technological revolution. Interestingly, in addition to helping obtain state-of-the-art results on a wide range of applications, the attention mechanism intrinsically provides meaningful insights on the internal behavior of the model. Can these insights be used as explanations? Debate rages on. In this paper, we mathematically study a simple attention-based architecture and pinpoint the differences between post-hoc and attention-based explanations. We show that they provide quite different results, and that, despite their limitations, post-hoc methods are capable of capturing more useful insights than merely examining the attention weights.
Code (1)
Similar Papers 제목 키워드 기반
Towards Mechanistic Interpretability of Graph Transformers via Attention Graphs
We introduce Attention Graphs, a new tool for mechanistic interpretability of Graph Neural Networks (GNNs) and Graph Transformers based on the mathematical equivalence between message passing in GNNs and the self-attenti…
Node ClassificationThe underlying structures of self-attention: symmetry, directionality, and emergent dynamics in Transformer training
Self-attention is essential to Transformer architectures, yet how information is embedded in the self-attention matrices and how different objective functions impact this process remains unclear. We present a mathematica…
When Differential Privacy Meets Interpretability: A Case Study
Given the increase in the use of personal data for training Deep Neural Networks (DNNs) in tasks such as medical imaging and diagnosis, differentially private training of DNNs is surging in importance and there is a larg…
Attention Meets Perturbations: Robust and Interpretable Attention with Adversarial Training
Although attention mechanisms have been applied to a variety of deep learning models and have been shown to improve the prediction performance, it has been reported to be vulnerable to perturbations to the mechanism. To …
When Pruning Meets Interpretability: Preserving Sparse Autoencoder Robustness in LLMs
Sparse autoencoders (SAEs) are widely used to interpret the internal representations of large language models (LLMs), yet their reliability under post-hoc model compression remains poorly understood. We present a systema…
Model Compression