相关论文: Kernelized Concept Erasure

The success of neural networks builds to a large extent on their ability to create internal knowledge representations from real-world high-dimensional data, such as images, sound, or text. Approaches to extract and present these…

Content-addressable memory, i.e. stored information that can be retrieved from content-based cues, is key to computation. Besides natural and artificial neural networks, physical learning systems have recently been shown to have remarkable…

Concept bottleneck models are interpretable predictive models that are often used in domains where model trust is a key priority, such as healthcare. They identify a small number of human-interpretable concepts in the data, which they then…

In many scenarios, human decisions are explained based on some high-level concepts. In this work, we take a step in the interpretability of neural networks by examining their internal representation or neuron's activations against concepts.…

Transformer language models (LMs) have been shown to represent concepts as directions in the latent space of hidden activations. However, for any human-interpretable concept, how can we find its direction in the latent space? We present a…

Despite substantial progress in applying neural networks (NN) to a wide variety of areas, they still largely suffer from a lack of transparency and interpretability. While recent developments in explainable artificial intelligence attempt…

Neural network-based language models deal with data sparsity problems by mapping the large discrete space of words into a smaller continuous space of real-valued vectors. By learning distributed vector representations for words, each…

Learning meaningful representations that maintain the content necessary for a particular task while filtering away detrimental variations is a problem of great interest in machine learning. In this paper, we tackle the problem of learning…

The ongoing exponential rise in recording capacity calls for new approaches for analysing and interpreting neural data. Effective dimensionality has emerged as an important property of neural activity across populations of neurons, yet…

Language carries implicit human biases, functioning both as a reflection and a perpetuation of stereotypes that people carry with them. Recently, ML-based NLP methods such as word embeddings have been shown to learn such language biases…

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…

This article deals with adversarial attacks towards deep learning systems for Natural Language Processing (NLP), in the context of privacy protection. We study a specific type of attack: an attacker eavesdrops on the hidden representations…

Learning continuous representations from unlabeled textual data has been increasingly studied for benefiting semi-supervised learning. Although it is relatively easier to interpret discrete representations, due to the difficulty of…

Continual learning studies how models can adapt to new tasks while retaining previously acquired knowledge. Although a broad spectrum of methods has been proposed to mitigate catastrophic forgetting, the field remains predominantly…

The majority of computer vision algorithms fail to find higher-order (abstract) patterns in an image so are not robust against adversarial attacks, unlike human lateralized vision. Deep learning considers each input pixel in a homogeneous…

Although neural models have achieved remarkable performance, they still encounter doubts due to the intransparency. To this end, model prediction explanation is attracting more and more attentions. However, current methods rarely…

To what extent does concept erasure eliminate generative capacity in diffusion models? While prior evaluations have primarily focused on measuring concept suppression under specific textual prompts, we explore a complementary and…

We propose a new kind of embedding for natural language text that deeply represents semantic meaning. Standard text embeddings use the outputs from hidden layers of a pretrained language model. In our method, we let a language model learn…

Advances in model editing through neuron pruning hold promise for removing undesirable concepts from large language models. However, it remains unclear whether models have the capacity to reacquire pruned concepts after editing. To…

A main challenge in mining network-based data is finding effective ways to represent or encode graph structures so that it can be efficiently exploited by machine learning algorithms. Several methods have focused in network representation…