English
Related papers

Related papers: White-box Testing of NLP models with Mask Neuron C…

200 papers

Due to the widespread application of deep neural networks~(DNNs) in safety-critical tasks, deep learning testing has drawn increasing attention. During the testing process, test cases that have been fuzzed or selected using test metrics are…

Software Engineering · Computer Science 2023-07-24 Dong Huang , Qingwen Bu , Yahao Qing , Yichao Fu , Heming Cui

Traditional benchmarking in NLP typically involves using static held-out test sets. However, this approach often results in an overestimation of performance and lacks the ability to offer comprehensive, interpretable, and dynamic…

Computation and Language · Computer Science 2024-11-08 Raoyuan Zhao , Abdullatif Köksal , Yihong Liu , Leonie Weissweiler , Anna Korhonen , Hinrich Schütze

Recently, deep learning models have been widely applied in program understanding tasks, and these models achieve state-of-the-art results on many benchmark datasets. A major challenge of deep learning for program understanding is that the…

Software Engineering · Computer Science 2024-01-02 Wenhan Wang , Yanzhou Li , Anran Li , Jian Zhang , Wei Ma , Yang Liu

People often listen to music in noisy environments, seeking to isolate themselves from ambient sounds. Indeed, a music signal can mask some of the noise's frequency components due to the effect of simultaneous masking. In this article, we…

Sound · Computer Science 2025-02-26 Clémentine Berger , Roland Badeau , Slim Essid

Checkpoints play an important role in training long running machine learning (ML) models. Checkpoints take a snapshot of an ML model and store it in a non-volatile memory so that they can be used to recover from failures to ensure rapid…

Existing approaches to explaining deep learning models in NLP usually suffer from two major drawbacks: (1) the main model and the explaining model are decoupled: an additional probing or surrogate model is used to interpret an existing…

Computation and Language · Computer Science 2020-12-10 Zijun Sun , Chun Fan , Qinghong Han , Xiaofei Sun , Yuxian Meng , Fei Wu , Jiwei Li

Deep neural networks (DNNs) have been widely applied in medical image classification and achieve remarkable classification performance. These achievements heavily depend on large-scale accurately annotated training data. However, label…

Computer Vision and Pattern Recognition · Computer Science 2023-06-19 Hongyang Jiang , Mengdi Gao , Yan Hu , Qiushi Ren , Zhaoheng Xie , Jiang Liu

Checklists are simple decision aids that are often used to promote safety and reliability in clinical applications. In this paper, we present a method to learn checklists for clinical decision support. We represent predictive checklists as…

Machine Learning · Computer Science 2022-01-19 Haoran Zhang , Quaid Morris , Berk Ustun , Marzyeh Ghassemi

A common approach to explaining NLP models is to use importance measures that express which tokens are important for a prediction. Unfortunately, such explanations are often wrong despite being persuasive. Therefore, it is essential to…

Computation and Language · Computer Science 2024-08-29 Andreas Madsen , Siva Reddy , Sarath Chandar

Model-based Reinforcement Learning (RL) is a popular learning paradigm due to its potential sample efficiency compared to model-free RL. However, existing empirical model-based RL approaches lack the ability to explore. This work studies a…

Machine Learning · Computer Science 2021-07-16 Yuda Song , Wen Sun

Sensitivity of deep-neural models to input noise is known to be a challenging problem. In NLP, model performance often deteriorates with naturally occurring noise, such as spelling errors. To mitigate this issue, models may leverage…

Computation and Language · Computer Science 2021-11-18 Jakub Náplava , Martin Popel , Milan Straka , Jana Straková

Fisher Vector classifiers and Deep Neural Networks (DNNs) are popular and successful algorithms for solving image classification problems. However, both are generally considered `black box' predictors as the non-linear transformations…

Computer Vision and Pattern Recognition · Computer Science 2015-12-02 Sebastian Bach , Alexander Binder , Grégoire Montavon , Klaus-Robert Müller , Wojciech Samek

Neuron analysis provides insights into how knowledge is structured in representations and discovers the role of neurons in the network. In addition to developing an understanding of our models, neuron analysis enables various applications…

Computation and Language · Computer Science 2023-05-29 Fahim Dalvi , Hassan Sajjad , Nadir Durrani

Learning with softmax cross-entropy on one-hot labels often leads to overconfident predictions and poor robustness under noise or perturbations. Label smoothing mitigates this by redistributing some confidence uniformly, but treats all…

Quantum Physics · Physics 2025-10-02 Fang Qi , Lu Peng , Zhengming Ding

Deep neural networks are widely used for classification. These deep models often suffer from a lack of interpretability -- they are particularly difficult to understand because of their non-linear nature. As a result, neural networks are…

Artificial Intelligence · Computer Science 2017-11-22 Oscar Li , Hao Liu , Chaofan Chen , Cynthia Rudin

From the latter half of the last decade, there has been a growing interest in developing algorithms for automatically solving mathematical word problems (MWP). It is a challenging and unique task that demands blending surface level text…

Computation and Language · Computer Science 2022-06-01 Sowmya S Sundaram , Sairam Gurajada , Marco Fisichella , Deepak P , Savitha Sam Abraham

This paper presents a model predictive control (MPC) for dynamic systems whose nonlinearity and uncertainty are modelled by deep neural networks (NNs), under input and state constraints. Since the NN output contains a high-order complex…

Systems and Control · Electrical Eng. & Systems 2024-05-20 Jianglin Lan

Current methods for Black-Box NLP interpretability, like LIME or SHAP, are based on altering the text to interpret by removing words and modeling the Black-Box response. In this paper, we outline limitations of this approach when using…

Computation and Language · Computer Science 2022-08-09 Yves Rychener , Xavier Renard , Djamé Seddah , Pascal Frossard , Marcin Detyniecki

Fine-tuning large language models (LLMs) for domain-specific tasks requires training datasets that comprehensively cover the target capabilities a practitioner needs. Yet identifying which capabilities a dataset fails to support, and doing…

Explanation methods shed light on the decision process of black-box classifiers such as deep neural networks. But their usefulness can be compromised because they are susceptible to manipulations. With this work, we aim to enhance the…

Machine Learning · Computer Science 2020-12-21 Ann-Kathrin Dombrowski , Christopher J. Anders , Klaus-Robert Müller , Pan Kessel