English
Related papers

Related papers: Attention Interpretability Across NLP Tasks

200 papers

Convolutional neural networks have been successfully applied to various NLP tasks. However, it is not obvious whether they model different linguistic patterns such as negation, intensification, and clause compositionality to help the…

Computation and Language · Computer Science 2018-10-23 Mahnaz Koupaee , William Yang Wang

We study the use of binary activated neural networks as interpretable and explainable predictors in the context of regression tasks on tabular data; more specifically, we provide guarantees on their expressiveness, present an approach based…

Machine Learning · Computer Science 2024-06-11 Benjamin Leblanc , Pascal Germain

We review generalized additive models as a type of ``transparent'' model that has recently seen renewed interest in the deep learning community as neural additive models. We highlight multiple types of nonidentifiability in this model class…

Machine Learning · Computer Science 2025-04-15 Xinyu Zhang , Julien Martinelli , ST John

Most recent work on interpretability of complex machine learning models has focused on estimating $\textit{a posteriori}$ explanations for previously trained models around specific predictions. $\textit{Self-explaining}$ models where…

Machine Learning · Computer Science 2018-12-05 David Alvarez-Melis , Tommi S. Jaakkola

Mechanistic Interpretability (MI) promises a path toward fully understanding how neural networks make their predictions. Prior work demonstrates that even when trained to perform simple arithmetic, models can implement a variety of…

Machine Learning · Computer Science 2024-05-28 Ouail Kitouni , Niklas Nolte , Víctor Samuel Pérez-Díaz , Sokratis Trifinopoulos , Mike Williams

Attention layers are widely used in natural language processing (NLP) and are beginning to influence computer vision architectures. Training very large transformer models allowed significant improvement in both fields, but once trained,…

Machine Learning · Computer Science 2021-05-21 Jean-Baptiste Cordonnier , Andreas Loukas , Martin Jaggi

This paper reviews recent studies in understanding neural-network representations and learning neural networks with interpretable/disentangled middle-layer representations. Although deep neural networks have exhibited superior performance…

Computer Vision and Pattern Recognition · Computer Science 2018-02-08 Quanshi Zhang , Song-Chun Zhu

An essential goal in mechanistic interpretability to decode a network, i.e., to convert a neural network's raw weights to an interpretable algorithm. Given the difficulty of the decoding problem, progress has been made to understand the…

Machine Learning · Computer Science 2023-12-07 Isaac Liao , Ziming Liu , Max Tegmark

Convolutional neural network (CNN) models have seen advanced improvements in performance in various domains, but lack of interpretability is a major barrier to assurance and regulation during operation for acceptance and deployment of…

Machine Learning · Computer Science 2022-11-02 Wenli Yang , Guan Huang , Renjie Li , Jiahao Yu , Yanyu Chen , Quan Bai , Beyong Kang

The multi-head self-attention mechanism of the transformer model has been thoroughly investigated recently. In one vein of study, researchers are interested in understanding why and how transformers work. In another vein, researchers…

Computation and Language · Computer Science 2022-10-28 Raymond Li , Wen Xiao , Linzi Xing , Lanjun Wang , Gabriel Murray , Giuseppe Carenini

This paper proposes a method to modify traditional convolutional neural networks (CNNs) into interpretable CNNs, in order to clarify knowledge representations in high conv-layers of CNNs. In an interpretable CNN, each filter in a high…

Computer Vision and Pattern Recognition · Computer Science 2018-02-15 Quanshi Zhang , Ying Nian Wu , Song-Chun Zhu

Saliency methods are widely used to interpret neural network predictions, but different variants of saliency methods often disagree even on the interpretations of the same prediction made by the same model. In these cases, how do we…

Computation and Language · Computer Science 2021-04-14 Shuoyang Ding , Philipp Koehn

Deep reinforcement learning techniques have demonstrated superior performance in a wide variety of environments. As improvements in training algorithms continue at a brisk pace, theoretical or empirical studies on understanding what these…

Machine Learning · Computer Science 2018-11-16 Raghuram Mandyam Annasamy , Katia Sycara

Interpretability of artificial intelligence (AI) methods, particularly deep neural networks, is of great interest. This heightened focus stems from the widespread use of AI-backed systems. These systems, often relying on intricate neural…

Quantum Physics · Physics 2024-11-11 Lirandë Pira , Chris Ferrie

Mechanistic interpretability research seeks to reveal the inner workings of large language models, yet most work focuses on classification or generative tasks rather than summarization. This paper presents an interpretability framework for…

Computation and Language · Computer Science 2025-05-26 Anurag Mishra

Annotator disagreement is widespread in NLP, particularly for subjective and ambiguous tasks such as toxicity detection and stance analysis. While early approaches treated disagreement as noise to be removed, recent work increasingly models…

Computation and Language · Computer Science 2026-01-21 Yinuo Xu , David Jurgens

The use of models, even if efficient, must be accompanied by an understanding at all levels of the process that transforms data (upstream and downstream). Thus, needs increase to define the relationships between individual data and the…

Machine Learning · Statistics 2022-09-02 Dimitri Delcaillau , Antoine Ly , Alize Papp , Franck Vermet

The ubiquity of neural networks (NNs) in real-world applications, from healthcare to natural language processing, underscores their immense utility in capturing complex relationships within high-dimensional data. However, NNs come with…

Machine Learning · Computer Science 2024-07-08 Chang Yue , Niraj K. Jha

In recent years, deep neural networks have been applied to obtain high performance of prediction, classification, and pattern recognition. However, the weights in these deep neural networks are difficult to be explained. Although a linear…

Machine Learning · Computer Science 2020-05-08 Chi-Hua Chen

A long time ago in the machine learning literature, the idea of incorporating a mechanism inspired by the human visual system into neural networks was introduced. This idea is named the attention mechanism, and it has gone through a long…

Machine Learning · Computer Science 2022-08-10 Derya Soydaner