English
Related papers

Related papers: Probing Classifiers are Unreliable for Concept Rem…

200 papers

A growing body of work makes use of probing to investigate the working of neural models, often considered black boxes. Recently, an ongoing debate emerged surrounding the limitations of the probing paradigm. In this work, we point out the…

Computation and Language · Computer Science 2021-02-22 Yanai Elazar , Shauli Ravfogel , Alon Jacovi , Yoav Goldberg

Classifiers tend to learn a false causal relationship between an over-represented concept and a label, which can result in over-reliance on the concept and compromised classification accuracy. It is imperative to have methods in place that…

Computation and Language · Computer Science 2023-07-06 Isar Nejadgholi , Svetlana Kiritchenko , Kathleen C. Fraser , Esma Balkır

While large-scale text-to-image diffusion models have demonstrated impressive image-generation capabilities, there are significant concerns about their potential misuse for generating unsafe content, violating copyright, and perpetuating…

Computer Vision and Pattern Recognition · Computer Science 2024-05-30 Ruchika Chavhan , Da Li , Timothy Hospedales

Detecting and classifying instances of hate in social media text has been a problem of interest in Natural Language Processing in the recent years. Our work leverages state of the art Transformer language models to identify hate speech in a…

Computation and Language · Computer Science 2021-01-12 Sayar Ghosh Roy , Ujwal Narayan , Tathagata Raha , Zubair Abid , Vasudeva Varma

We consider the problem of a neural network being requested to classify images (or other inputs) without making implicit use of a "protected concept", that is a concept that should not play any role in the decision of the network. Typically…

Machine Learning · Computer Science 2019-01-09 Sen Jia , Thomas Lansdall-Welfare , Nello Cristianini

Deep neural networks are vulnerable to adversarial attacks, where a small perturbation to an input alters the model prediction. In many cases, malicious inputs intentionally crafted for one model can fool another model. In this paper, we…

Machine Learning · Computer Science 2021-09-23 Liping Yuan , Xiaoqing Zheng , Yi Zhou , Cho-Jui Hsieh , Kai-wei Chang

Hate speech classifiers trained on imbalanced datasets struggle to determine if group identifiers like "gay" or "black" are used in offensive or prejudiced ways. Such biases manifest in false positives when these identifiers are present,…

Computation and Language · Computer Science 2020-07-08 Brendan Kennedy , Xisen Jin , Aida Mostafazadeh Davani , Morteza Dehghani , Xiang Ren

Convolutional neural networks have been used to achieve a string of successes during recent years, but their lack of interpretability remains a serious issue. Adversarial examples are designed to deliberately fool neural networks into…

Machine Learning · Computer Science 2020-04-28 Jan Philip Göpfert , André Artelt , Heiko Wersing , Barbara Hammer

Anchors (Ribeiro et al., 2018) is a post-hoc, rule-based interpretability method. For text data, it proposes to explain a decision by highlighting a small set of words (an anchor) such that the model to explain has similar outputs when they…

Machine Learning · Statistics 2025-10-22 Gianluigi Lopardo , Frederic Precioso , Damien Garreau

Methods for erasing human-interpretable concepts from neural representations that assume linearity have been found to be tractable and useful. However, the impact of this removal on the behavior of downstream classifiers trained on the…

Machine Learning · Computer Science 2024-05-14 Shauli Ravfogel , Yoav Goldberg , Ryan Cotterell

Although neural models have achieved impressive results on several NLP benchmarks, little is understood about the mechanisms they use to perform language tasks. Thus, much recent attention has been devoted to analyzing the sentence…

Computation and Language · Computer Science 2021-03-09 Abhilasha Ravichander , Yonatan Belinkov , Eduard Hovy

Concept-based explanations have emerged as a popular way of extracting human-interpretable representations from deep discriminative models. At the same time, the disentanglement learning literature has focused on extracting similar…

Machine Learning · Computer Science 2021-04-15 Dmitry Kazhdan , Botty Dimanov , Helena Andres Terre , Mateja Jamnik , Pietro Liò , Adrian Weller

Memorization in large-scale text-to-image diffusion models poses significant security and intellectual property risks, enabling adversarial attribute extraction and the unauthorized reproduction of sensitive or proprietary features. While…

Machine Learning · Computer Science 2026-01-28 Divya Kothandaraman , Jaclyn Pytlarz

The use of algorithmic (learning-based) decision making in scenarios that affect human lives has motivated a number of recent studies to investigate such decision making systems for potential unfairness, such as discrimination against…

Machine Learning · Computer Science 2021-05-11 Junaid Ali , Muhammad Bilal Zafar , Adish Singla , Krishna P. Gummadi

Concept-based explainability methods provide insight into deep learning systems by constructing explanations using human-understandable concepts. While the literature on human reasoning demonstrates that we exploit relationships between…

Machine Learning · Computer Science 2024-05-29 Naveen Raman , Mateo Espinosa Zarlenga , Mateja Jamnik

In explainable AI, Concept Activation Vectors (CAVs) are typically obtained by training linear classifier probes to detect human-understandable concepts as directions in the activation space of deep neural networks. It is widely assumed…

Artificial Intelligence · Computer Science 2025-11-07 Jacob Lysnæs-Larsen , Marte Eggen , Inga Strümke

Many applications of data-driven models demand transparency of decisions, especially in health care, criminal justice, and other high-stakes environments. Modern trends in machine learning research have led to algorithms that are…

Machine Learning · Computer Science 2022-05-09 Zachariah Carmichael , Walter J. Scheirer

Explainable artificial intelligence has rapidly emerged since lawmakers have started requiring interpretable models for safety-critical domains. Concept-based neural networks have arisen as explainable-by-design methods as they leverage…

Artificial Intelligence · Computer Science 2023-09-28 Pietro Barbiero , Gabriele Ciravegna , Francesco Giannini , Pietro Lió , Marco Gori , Stefano Melacci

Adversarial purification is one of the promising approaches to defend neural networks against adversarial attacks. Recently, methods utilizing diffusion probabilistic models have achieved great success for adversarial purification in image…

Computer Vision and Pattern Recognition · Computer Science 2024-08-13 Mingkun Zhang , Jianing Li , Wei Chen , Jiafeng Guo , Xueqi Cheng

Pre-trained language models have been successful on text classification tasks, but are prone to learning spurious correlations from biased datasets, and are thus vulnerable when making inferences in a new domain. Prior work reveals such…

Computation and Language · Computer Science 2022-01-03 Huihan Yao , Ying Chen , Qinyuan Ye , Xisen Jin , Xiang Ren
‹ Prev 1 4 5 6 7 8 10 Next ›