English
Related papers

Related papers: Probing Classifiers are Unreliable for Concept Rem…

200 papers

We address the problem of concept removal in deep neural networks, aiming to learn representations that do not encode certain specified concepts (e.g., gender etc.) We propose a novel method based on adversarial linear classifiers trained…

Machine Learning · Computer Science 2023-10-10 Yegor Klochkov , Jean-Francois Ton , Ruocheng Guo , Yang Liu , Hang Li

The emergence of large-scale pretrained language models has posed unprecedented challenges in deriving explanations of why the model has made some predictions. Stemmed from the compositional nature of languages, spurious correlations have…

Computation and Language · Computer Science 2023-05-04 Ruochen Zhao , Shafiq Joty , Yongjie Wang , Tan Wang

Concept probing has recently gained popularity as a way for humans to peek into what is encoded within artificial neural networks. In concept probing, additional classifiers are trained to map the internal representations of a model into…

Machine Learning · Computer Science 2025-07-28 Manuel de Sousa Ribeiro , Afonso Leote , João Leite

Text-to-image generative models can produce photo-realistic images for an extremely broad range of concepts, and their usage has proliferated widely among the general public. On the flip side, these models have numerous drawbacks, including…

Machine Learning · Computer Science 2023-10-10 Minh Pham , Kelly O. Marshall , Niv Cohen , Govind Mittal , Chinmay Hegde

Probing classifiers have emerged as one of the prominent methodologies for interpreting and analyzing deep neural network models of natural language processing. The basic idea is simple -- a classifier is trained to predict some linguistic…

Computation and Language · Computer Science 2021-09-23 Yonatan Belinkov

Concept probing has recently garnered increasing interest as a way to help interpret artificial neural networks, dealing both with their typically large size and their subsymbolic nature, which ultimately renders them unfeasible for direct…

Artificial Intelligence · Computer Science 2025-07-25 Manuel de Sousa Ribeiro , Afonso Leote , João Leite

To improve trust and transparency, it is crucial to be able to interpret the decisions of Deep Neural classifiers (DNNs). Instance-level examinations, such as attribution techniques, are commonly employed to interpret the model decisions.…

Machine Learning · Computer Science 2025-03-13 Youngju Joung , Sehyun Lee , Jaesik Choi

Interpreting the inner workings of deep learning models is crucial for establishing trust and ensuring model safety. Concept-based explanations have emerged as a superior approach that is more interpretable than feature attribution…

Machine Learning · Computer Science 2023-07-17 Mara Graziani , Laura O' Mahony , An-Phi Nguyen , Henning Müller , Vincent Andrearczyk

The most common methods in explainable artificial intelligence are post-hoc techniques which identify the most relevant features used by pretrained opaque models. Some of the most advanced post hoc methods can generate explanations that…

Artificial Intelligence · Computer Science 2026-03-11 Stefano Fioravanti , Francesco Giannini , Paolo Frazzetto , Fabio Zanasi , Pietro Barbiero

This paper presents a novel concept learning framework for enhancing model interpretability and performance in visual classification tasks. Our approach appends an unsupervised explanation generator to the primary classifier network and…

Computer Vision and Pattern Recognition · Computer Science 2024-04-04 Tanmay Garg , Deepika Vemuri , Vineeth N Balasubramanian

Deep Learning methods are renowned for their performances, yet their lack of interpretability prevents them from high-stakes contexts. Recent model agnostic methods address this problem by providing post-hoc interpretability methods by…

Machine Learning · Computer Science 2021-11-30 Marco Repetto

In current AI era, users may request AI companies to delete their data from the training dataset due to the privacy concerns. As a model owner, retraining a model will consume significant computational resources. Therefore, machine…

Machine Learning · Computer Science 2024-05-27 Wenhan Chang , Tianqing Zhu , Heng Xu , Wenjian Liu , Wanlei Zhou

Interest in understanding and factorizing learned embedding spaces through conceptual explanations is steadily growing. When no human concept labels are available, concept discovery methods search trained embedding spaces for interpretable…

Machine Learning · Statistics 2023-06-07 Tobias Leemann , Michael Kirchhof , Yao Rong , Enkelejda Kasneci , Gjergji Kasneci

Recent advances in Representation Learning and Adversarial Training seem to succeed in removing unwanted features from the learned representation. We show that demographic information of authors is encoded in -- and can be recovered from --…

Computation and Language · Computer Science 2018-09-05 Yanai Elazar , Yoav Goldberg

Despite the impressive capabilities of generating images, text-to-image diffusion models are susceptible to producing undesirable outputs such as NSFW content and copyrighted artworks. To address this issue, recent studies have focused on…

Computer Vision and Pattern Recognition · Computer Science 2024-05-28 Tianyun Yang , Juan Cao , Chang Xu

Concept-based interpretability methods aim to explain deep neural network model predictions using a predefined set of semantic concepts. These methods evaluate a trained model on a new, "probe" dataset and correlate model predictions with…

Computer Vision and Pattern Recognition · Computer Science 2023-05-15 Vikram V. Ramaswamy , Sunnie S. Y. Kim , Ruth Fong , Olga Russakovsky

Recent work on interpretability has focused on concept-based explanations, where deep learning models are explained in terms of high-level units of information, referred to as concepts. Concept learning models, however, have been shown to…

Machine Learning · Computer Science 2023-10-02 Mateo Espinosa Zarlenga , Pietro Barbiero , Zohreh Shams , Dmitry Kazhdan , Umang Bhatt , Adrian Weller , Mateja Jamnik

Modern neural models trained on textual data rely on pre-trained representations that emerge without direct supervision. As these representations are increasingly being used in real-world applications, the inability to \emph{control} their…

Machine Learning · Computer Science 2024-12-18 Shauli Ravfogel , Michael Twiton , Yoav Goldberg , Ryan Cotterell

Ensuring fairness in NLP models is crucial, as they often encode sensitive attributes like gender and ethnicity, leading to biased outcomes. Current concept erasure methods attempt to mitigate this by modifying final latent representations…

Computation and Language · Computer Science 2024-10-17 Fanny Jourdan , Louis Béthune , Agustin Picard , Laurent Risser , Nicholas Asher

Bias in classifiers is a severe issue of modern deep learning methods, especially for their application in safety- and security-critical areas. Often, the bias of a classifier is a direct consequence of a bias in the training dataset,…

Computer Vision and Pattern Recognition · Computer Science 2021-03-11 Christian Reimers , Paul Bodesheim , Jakob Runge , Joachim Denzler
‹ Prev 1 2 3 10 Next ›