相关论文: Is Attention Interpretable?

Pre-trained language models (PLMs) like BERT are being used for almost all language-related tasks, but interpreting their behavior still remains a significant challenge and many important questions remain largely unanswered. In this work,…

Attention mechanisms are a central property of cognitive systems allowing them to selectively deploy cognitive resources in a flexible manner. Attention has been long studied in the neurosciences and there are numerous phenomenological…

Attention is an important mechanism that can be employed for a variety of deep learning models across many different domains and tasks. This survey provides an overview of the most important attention mechanisms proposed in the literature.…

Text reviews can provide rich useful semantic information for modeling users and items, which can benefit rating prediction in recommendation. Different words and reviews may have different informativeness for users or items. Besides,…

Learned dynamic weighting of the conditioning signal (attention) has been shown to improve neural language generation in a variety of settings. The weights applied when generating a particular output sequence have also been viewed as…

Attention is a key component of the now ubiquitous pre-trained language models. By learning to focus on relevant pieces of information, these Transformer-based architectures have proven capable of tackling several tasks at once and…

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…

Complex machine learning algorithms are used more and more often in critical tasks involving text data, leading to the development of interpretability methods. Among local methods, two families have emerged: those computing importance…

In this paper, we address the "black-box" problem in predictive process analytics by building interpretable models that are capable to inform both what and why is a prediction. Predictive process analytics is a newly emerged discipline…

The state of the art in learning meaningful semantic representations of words is the Transformer model and its attention mechanisms. Simply put, the attention mechanisms learn to attend to specific parts of the input dispensing recurrence…

Attention-based transformer models have achieved remarkable progress in multi-modal tasks, such as visual question answering. The explainability of attention-based methods has recently attracted wide interest as it can explain the inner…

Image classification models have achieved satisfactory performance on many datasets, sometimes even better than human. However, The model attention is unclear since the lack of interpretability. This paper investigates the fidelity and…

Understanding how Large Language Models (LLMs) process information from prompts remains a significant challenge. To shed light on this "black box," attention visualization techniques have been developed to capture neuron-level perceptions…

In the past few years, attention mechanisms have become an indispensable component of end-to-end neural machine translation models. However, previous attention models always refer to some source words when predicting a target word, which…

Explainable AI (XAI) has become increasingly important with the rise of large transformer models, yet many explanation methods designed for CNNs transfer poorly to Vision Transformers (ViTs). Existing ViT explanations often rely on…

The performance of relation extraction models has increased considerably with the rise of neural networks. However, a key issue of neural relation extraction is robustness: the models do not scale well to long sentences with multiple…

Recently, much progress has been made in learning general-purpose sentence representations that can be used across domains. However, most of the existing models typically treat each word in a sentence equally. In contrast, extensive studies…

Multi-headed attention heads are a mainstay in transformer-based models. Different methods have been proposed to classify the role of each attention head based on the relations between tokens which have high pair-wise attention. These roles…

[Purpose] To understand the meaning of a sentence, humans can focus on important words in the sentence, which reflects our eyes staying on each word in different gaze time or times. Thus, some studies utilize eye-tracking values to optimize…

Interpreting the inner workings of neural models is a key step in ensuring the robustness and trustworthiness of the models, but work on neural network interpretability typically faces a trade-off: either the models are too constrained to…