English
Related papers

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

200 papers

With the dramatic advances in deep learning technology, machine learning research is focusing on improving the interpretability of model predictions as well as prediction performance in both basic and applied research. While deep learning…

Machine Learning · Computer Science 2024-01-24 Shunsuke Kitada

Gradient-based optimization is the workhorse of deep learning, offering efficient and scalable training via backpropagation. However, exposing gradients during training can leak sensitive information about the underlying data, raising…

Machine Learning · Computer Science 2026-01-06 Ismail Labiad , Mathurin Videau , Matthieu Kowalski , Marc Schoenauer , Alessandro Leite , Julia Kempe , Olivier Teytaud

To explain NLP models a popular approach is to use importance measures, such as attention, which inform input tokens are important for making a prediction. However, an open question is how well these explanations accurately reflect a…

Computation and Language · Computer Science 2022-11-02 Andreas Madsen , Nicholas Meade , Vaibhav Adlakha , Siva Reddy

The Neural Network (NN), as a black-box function approximator, has been considered in many control and robotics applications. However, difficulties in verifying the overall system safety in the presence of uncertainties hinder the…

Robotics · Computer Science 2024-05-21 Xiao Li , Yutong Li , Anouck Girard , Ilya Kolmanovsky

Many Machine Learning algorithms, such as deep neural networks, have long been criticized for being "black-boxes"-a kind of models unable to provide how it arrive at a decision without further efforts to interpret. This problem has raised…

Machine Learning · Statistics 2019-07-04 Yihuang Kang , I-Ling Cheng , Wenjui Mao , Bowen Kuo , Pei-Ju Lee

Hallucinations are a persistent problem with Large Language Models (LLMs). As these models become increasingly used in high-stakes domains, such as healthcare and finance, the need for effective hallucination detection is crucial. To this…

Computation and Language · Computer Science 2026-01-29 Dylan Bouchard , Mohit Singh Chauhan

We present a critical review of Neural Coverage (NLC), a state-of-the-art DNN coverage criterion by Yuan et al. at ICSE 2023. While NLC proposes to satisfy eight design requirements and demonstrates strong empirical performance, we question…

Software Engineering · Computer Science 2026-01-14 Jinhan Kim , Nargiz Humbatova , Gunel Jahangirova , Shin Yoo , Paolo Tonella

Exceptional mathematical reasoning ability is one of the key features that demonstrate the power of large language models (LLMs). How to comprehensively define and evaluate the mathematical abilities of LLMs, and even reflect the user…

Computation and Language · Computer Science 2024-10-10 Zihao Zhou , Shudong Liu , Maizhen Ning , Wei Liu , Jindong Wang , Derek F. Wong , Xiaowei Huang , Qiufeng Wang , Kaizhu Huang

This article proposes a test procedure that can be used to test ML models and ML-based systems independently of the actual training process. In this way, the typical quality statements such as accuracy and precision of these models and…

Machine Learning · Computer Science 2024-06-21 Hans-Werner Wiesbrock , Jürgen Großmann

Deep neural networks (DNNs) have demonstrated impressive performance on many challenging machine learning tasks. However, DNNs are vulnerable to adversarial inputs generated by adding maliciously crafted perturbations to the benign inputs.…

Machine Learning · Computer Science 2019-10-29 Ka-Ho Chow , Wenqi Wei , Yanzhao Wu , Ling Liu

Neural networks are ubiquitous. However, they are often sensitive to small input changes. Hence, to prevent unexpected behavior in safety-critical applications, their formal verification -- a notoriously hard problem -- is necessary. Many…

Machine Learning · Computer Science 2026-02-10 Lukas Koller , Tobias Ladner , Matthias Althoff

Recent technological advancements have led to a large number of patents in a diverse range of domains, making it challenging for human experts to analyze and manage. State-of-the-art methods for multi-label patent classification rely on…

Artificial Intelligence · Computer Science 2024-07-30 Md Shajalal , Sebastian Denef , Md. Rezaul Karim , Alexander Boden , Gunnar Stevens

Reliably predicting the behavior of language models -- such as whether their outputs are correct or have been adversarially manipulated -- is a fundamentally challenging task. This is often made even more difficult as frontier language…

Machine Learning · Computer Science 2025-12-02 Dylan Sam , Marc Finzi , J. Zico Kolter

We address the need to generate faithful explanations of "black box" Deep Learning models. Several tests have been proposed to determine aspects of faithfulness of explanation methods, but they lack cross-domain applicability and a rigorous…

Machine Learning · Computer Science 2023-06-27 Harshinee Sriram , Cristina Conati

Modern deep learning models for NLP are notoriously opaque. This has motivated the development of methods for interpreting such models, e.g., via gradient-based saliency maps or the visualization of attention weights. Such approaches aim to…

Computation and Language · Computer Science 2020-05-15 Xiaochuang Han , Byron C. Wallace , Yulia Tsvetkov

Deep learning models are favored in many research and industry areas and have reached the accuracy of approximating or even surpassing human level. However they've long been considered by researchers as black-box models for their…

Machine Learning · Computer Science 2020-10-16 Xiaojian Wang , Jingyuan Wang , Ke Tang

To demystify the "black box" property of deep neural networks for natural language processing (NLP), several methods have been proposed to interpret their predictions by measuring the change in prediction probability after erasing each…

Computation and Language · Computer Science 2020-10-28 Siwon Kim , Jihun Yi , Eunji Kim , Sungroh Yoon

Deep neural network (DNN) models have achieved phenomenal success for applications in many domains, ranging from academic research in science and engineering to industry and business. The modeling power of DNN is believed to have come from…

Machine Learning · Computer Science 2024-10-08 Beomseok Seo , Lin Lin , Jia Li

Recently, Large Language Models (LLMs) have witnessed remarkable performance as zero-shot task planners for robotic manipulation tasks. However, the open-loop nature of previous works makes LLM-based planning error-prone and fragile. On the…

Robotics · Computer Science 2025-03-18 Zhi Zheng , Qian Feng , Hang Li , Alois Knoll , Jianxiang Feng

Confidence calibration is a major concern when applying artificial neural networks in safety-critical applications. Since most research in this area has focused on classification in the past, confidence calibration in the scope of object…

Computer Vision and Pattern Recognition · Computer Science 2021-01-11 Franziska Schwaiger , Maximilian Henne , Fabian Küppers , Felippe Schmoeller Roza , Karsten Roscher , Anselm Haselhoff