English
Related papers

Related papers: Attention Interpretability Across NLP Tasks

200 papers

Neural IR architectures, particularly cross-encoders, are highly effective models whose internal mechanisms are mostly unknown. Most works trying to explain their behavior focused on high-level processes (e.g., what in the input influences…

Information Retrieval · Computer Science 2025-07-22 Mathias Vast , Basile Van Cooten , Laure Soulier , Benjamin Piwowarski

We take inspiration from the study of human explanation to inform the design and evaluation of interpretability methods in machine learning. First, we survey the literature on human explanation in philosophy, cognitive science, and the…

Artificial Intelligence · Computer Science 2021-09-21 David Alvarez-Melis , Harmanpreet Kaur , Hal Daumé , Hanna Wallach , Jennifer Wortman Vaughan

Mechanistic interpretability aims to understand model behaviors in terms of specific, interpretable features, often hypothesized to manifest as low-dimensional subspaces of activations. Specifically, recent studies have explored subspace…

Machine Learning · Computer Science 2023-12-07 Aleksandar Makelov , Georg Lange , Neel Nanda

Transformer-based models have become state-of-the-art tools in various machine learning tasks, including time series classification, yet their complexity makes understanding their internal decision-making challenging. Existing…

Machine Learning · Computer Science 2025-11-27 Matīss Kalnāre , Sofoklis Kitharidis , Thomas Bäck , Niki van Stein

Text embeddings are a fundamental component in many NLP tasks, including classification, regression, clustering, and semantic search. However, despite their ubiquitous application, challenges persist in interpreting embeddings and…

Computation and Language · Computer Science 2025-10-03 Juri Opitz , Lucas Möller , Andrianos Michail , Sebastian Padó , Simon Clematide

Interpretable brain network models for disease prediction are of great value for the advancement of neuroscience. GNNs are promising to model complicated network data, but they are prone to overfitting and suffer from poor interpretability,…

Machine Learning · Computer Science 2021-07-13 Hejie Cui , Wei Dai , Yanqiao Zhu , Xiaoxiao Li , Lifang He , Carl Yang

Machine Learning (ML) models are often complex and difficult to interpret due to their 'black-box' characteristics. Interpretability of a ML model is usually defined as the degree to which a human can understand the cause of decisions…

Methodology · Statistics 2020-06-25 Simon Kocbek , Primoz Kocbek , Leona Cilar , Gregor Stiglic

Sometimes it is not enough for a DNN to produce an outcome. For example, in applications such as healthcare, users need to understand the rationale of the decisions. Therefore, it is imperative to develop algorithms to learn models with…

Machine Learning · Computer Science 2019-01-29 Yinpeng Dong , Fan Bao , Hang Su , Jun Zhu

We describe an "interpretability illusion" that arises when analyzing the BERT model. Activations of individual neurons in the network may spuriously appear to encode a single, simple concept, when in fact they are encoding something far…

Computation and Language · Computer Science 2021-04-16 Tolga Bolukbasi , Adam Pearce , Ann Yuan , Andy Coenen , Emily Reif , Fernanda Viégas , Martin Wattenberg

Attention based explanations (viz. saliency maps), by providing interpretability to black box models such as deep neural networks, are assumed to improve human trust and reliance in the underlying models. Recently, it has been shown that…

Human-Computer Interaction · Computer Science 2022-01-28 Arjun R Akula , Song-Chun Zhu

Interpretability is an elusive but highly sought-after characteristic of modern machine learning methods. Recent work has focused on interpretability via $\textit{explanations}$, which justify individual model predictions. In this work, we…

Machine Learning · Computer Science 2019-10-31 David Alvarez-Melis , Hal Daumé , Jennifer Wortman Vaughan , Hanna Wallach

Recent years have witnessed the emergence of a variety of post-hoc interpretations that aim to uncover how natural language processing (NLP) models make predictions. Despite the surge of new interpretation methods, it remains an open…

Computation and Language · Computer Science 2022-04-04 Fan Yin , Zhouxing Shi , Cho-Jui Hsieh , Kai-Wei Chang

The attention mechanisim is appealing for neural machine translation, since it is able to dynam- ically encode a source sentence by generating a alignment between a target word and source words. Unfortunately, it has been proved to be worse…

Computation and Language · Computer Science 2016-09-15 Lemao Liu , Masao Utiyama , Andrew Finch , Eiichiro Sumita

The term "interpretability" is oftenly used by machine learning researchers each with their own intuitive understanding of it. There is no universal well agreed upon definition of interpretability in machine learning. As any type of science…

Machine Learning · Computer Science 2018-07-26 Abdul Karim , Avinash Mishra , MA Hakim Newton , Abdul Sattar

When developing AI systems that interact with humans, it is essential to design both a system that can understand humans, and a system that humans can understand. Most deep network based agent-modeling approaches are 1) not interpretable…

Machine Learning · Computer Science 2021-07-14 Ini Oguntola , Dana Hughes , Katia Sycara

Convolutional Neural Networks have achieved impressive results in various tasks, but interpreting the internal mechanism is a challenging problem. To tackle this problem, we exploit a multi-channel attention mechanism in feature space. Our…

Computer Vision and Pattern Recognition · Computer Science 2019-05-01 Masanari Kimura , Masayuki Tanaka

To tackle interpretability in deep learning, we present a novel framework to jointly learn a predictive model and its associated interpretation model. The interpreter provides both local and global interpretability about the predictive…

Machine Learning · Computer Science 2022-02-24 Jayneel Parekh , Pavlo Mozharovskyi , Florence d'Alché-Buc

Interpretable machine learning models offer understandable reasoning behind their decision-making process, though they may not always match the performance of their black-box counterparts. This trade-off between interpretability and model…

Artificial Intelligence · Computer Science 2025-03-12 Pranjal Atrey , Michael P. Brundage , Min Wu , Sanghamitra Dutta

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…

Machine Learning · Computer Science 2024-07-02 Maciej Żelaszczyk , Jacek Mańdziuk

Natural language processing has greatly benefited from the introduction of the attention mechanism. However, standard attention models are of limited interpretability for tasks that involve a series of inference steps. We describe an…

Computation and Language · Computer Science 2018-09-03 Martin Tutek , Jan Šnajder