Related papers: Human Guided Exploitation of Interpretable Attenti…
Transformer-based language models have achieved impressive success in various natural language processing tasks due to their ability to capture complex dependencies and contextual information using self-attention mechanisms. However, they…
Multi-head attention advances neural machine translation by working out multiple versions of attention in different subspaces, but the neglect of semantic overlapping between subspaces increases the difficulty of translation and…
While the Transformer architecture has become ubiquitous in the machine learning field, its adaptation to 3D shape recognition is non-trivial. Due to its quadratic computational complexity, the self-attention operator quickly becomes…
Mechanistic interpretability seeks to reverse engineer a trained neural network by identifying the minimal subset of internal components. We perform a mechanistic interpretability analysis of the Particle Transformer architecture, trained…
Conventional wisdom suggests that pre-training Vision Transformers (ViT) improves downstream performance by learning useful representations. Is this actually true? We investigate this question and find that the features and representations…
Despite an in-principle understanding of self-attention matrix operations in Transformer language models (LMs), it remains unclear precisely how these operations map onto interpretable computations or functions--and how or when individual…
Transformer architectures have achieved state-of-the-art results on a variety of sequence modeling tasks. However, their attention mechanism comes with a quadratic complexity in sequence lengths, making the computational overhead…
Transformers have been proven a successful model for a variety of tasks in sequence modeling. However, computing the attention matrix, which is their key component, has quadratic complexity with respect to the sequence length, thus making…
While pretrained models such as BERT have shown large gains across natural language understanding tasks, their performance can be improved by further training the model on a data-rich intermediate task, before fine-tuning it on a target…
Transformer-based models, such as BERT and GPT, have been widely adopted in natural language processing (NLP) due to their exceptional performance. However, recent studies show their vulnerability to textual adversarial attacks where the…
Transformer architectures deliver state-of-the-art accuracy via dense full-attention, but their quadratic time and memory complexity with respect to sequence length limits practical deployment. Linear attention mechanisms offer linear or…
Neural language models are becoming the prevailing methodology for the tasks of query answering, text classification, disambiguation, completion and translation. Commonly comprised of hundreds of millions of parameters, these neural network…
Transformer-based Large Language Models (LLMs) are the state-of-the-art for natural language tasks. Recent work has attempted to decode, by reverse engineering the role of linear layers, the internal mechanisms by which LLMs arrive at their…
Transformers have achieved remarkable successes across a wide range of applications, yet the theoretical foundation of their model efficiency remains underexplored. In this work, we investigate how the model parameters -- mainly attention…
Recurrent neural networks with differentiable attention mechanisms have had success in generative and classification tasks. We show that the classification performance of such models can be enhanced by guiding a randomly initialized model…
Language models for code such as CodeBERT offer the capability to learn advanced source code representation, but their opacity poses barriers to understanding of captured properties. Recent attention analysis studies provide initial…
Developing neural architectures that are capable of logical reasoning has become increasingly important for a wide range of applications (e.g., natural language processing). Towards this grand objective, we propose a symbolic reasoning…
This paper proposes a general interpretable predictive system with shared information. The system is able to perform predictions in a multi-task setting where distinct tasks are not bound to have the same input/output structure. Embeddings…
Central to the success of Transformers is the attention block, which effectively models global dependencies among input tokens associated to a dataset. However, we theoretically demonstrate that standard attention mechanisms in transformers…
Pre-trained Transformer-based models have achieved state-of-the-art performance for various Natural Language Processing (NLP) tasks. However, these models often have billions of parameters, and, thus, are too resource-hungry and…