相关论文: Null It Out: Guarding Protected Attributes by Iter…

Natural language processing models tend to learn and encode social biases present in the data. One popular approach for addressing such biases is to eliminate encoded information from the model's representations. However, current methods…

Bias elimination and recent probing studies attempt to remove specific information from embedding spaces. Here it is important to remove as much of the target information as possible, while preserving any other information present. INLP is…

Amnesic probing is a technique used to examine the influence of specific linguistic information on the behaviour of a model. This involves identifying and removing the relevant information and then assessing whether the model's performance…

Ensuring that neural models used in real-world applications cannot infer sensitive information, such as demographic attributes like gender or race, from text representations is a critical challenge when fairness is a concern. We address…

While Large Language Models (LLMs) have demonstrated impressive performance in various domains and tasks, concerns about their safety are becoming increasingly severe. In particular, since models may store unsafe knowledge internally,…

We introduce a novel, closed-form approach for selective unlearning in multimodal models, specifically targeting pretrained models such as CLIP. Our method leverages nullspace projection to erase the target class information embedded in the…

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…

While neural networks have been successfully applied to many natural language processing tasks, they come at the cost of interpretability. In this paper, we propose a general methodology to analyze and interpret decisions from a neural…

One of the pursued objectives of deep learning is to provide tools that learn abstract representations of reality from the observation of multiple contextual situations. More precisely, one wishes to extract disentangled representations…

In this paper, we propose a novel approach for implicit data representation to evaluate similarity of input data using a trained neural network. In contrast to the previous approach, which uses gradients for representation, we utilize only…

Imaging inverse problems aim to recover high-dimensional signals from undersampled, noisy measurements, a fundamentally ill-posed task with infinite solutions in the null-space of the sensing operator. To resolve this ambiguity, prior…

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…

Since the recent advent of regulations for data protection (e.g., the General Data Protection Regulation), there has been increasing demand in deleting information learned from sensitive data in pre-trained models without retraining from…

Projections (or dimensionality reduction) methods $P$ aim to map high-dimensional data to typically 2D scatterplots for visual exploration. Inverse projection methods $P^{-1}$ aim to map this 2D space to the data space to support tasks such…

Cross-lingual natural language processing relies on translation, either by humans or machines, at different levels, from translating training data to translating test sets. However, compared to original texts in the same language,…

Machine learning models (mainly neural networks) are used more and more in real life. Users feed their data to the model for training. But these processes are often one-way. Once trained, the model remembers the data. Even when data is…

Implicit Neural Representations (INRs) have emerged as a paradigm in knowledge representation, offering exceptional flexibility and performance across a diverse range of applications. INRs leverage multilayer perceptrons (MLPs) to model…

We propose to learn invariant representations, in the data domain, to achieve interpretability in algorithmic fairness. Invariance implies a selectivity for high level, relevant correlations w.r.t. class label annotations, and a robustness…

Machine unlearning seeks to remove the influence of specific training data from a model, a need driven by privacy regulations and robustness concerns. Existing approaches typically modify model parameters, but such updates can be unstable,…

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…