Related papers: Discovering Salient Neurons in Deep NLP Models

While end-to-end learning with fully differentiable models has enabled tremendous success in natural language process (NLP) and machine learning, there have been significant recent interests in learning with latent discrete structures to…

Recent developments in transformer-based language models have allowed them to capture a wide variety of world knowledge that can be adapted to downstream tasks with limited resources. However, what pieces of information are understood in…

Recent advances in natural language processing (NLP) have produced general models that can perform complex tasks such as summarizing long passages and translating across languages. Here, we introduce a method to extract adjective…

A neural language model trained on a text corpus can be used to induce distributed representations of words, such that similar words end up with similar representations. If the corpus is multilingual, the same model can be used to learn…

Recent breakthroughs in Natural Language Processing (NLP) have been driven by language models trained on a massive amount of plain text. While powerful, deriving supervision from textual resources is still an open question. For example,…

Understanding the latent space geometry of large language models (LLMs) is key to interpreting their behavior and improving alignment. Yet it remains unclear to what extent LLMs linearly organize representations related to semantic…

We reassess the Knowledge Neuron (KN) Thesis: an interpretation of the mechanism underlying the ability of large language models to recall facts from a training corpus. This nascent thesis proposes that facts are recalled from the training…

Latent representation learned from multi-layered neural networks via hierarchical feature abstraction enables recent success of deep learning. Under the deep learning framework, generalization performance highly depends on the learned…

Computer vision algorithms with pixel-wise labeling tasks, such as semantic segmentation and salient object detection, have gone through a significant accuracy increase with the incorporation of deep learning. Deep segmentation methods…

Deep learning models have achieved remarkable success in natural language inference (NLI) tasks. While these models are widely explored, they are hard to interpret and it is often unclear how and why they actually work. In this paper, we…

Understanding how humans process natural language has long been a vital research direction. The field of natural language processing (NLP) has recently experienced a surge in the development of powerful language models. These models have…

The last decades have seen great progress in saliency prediction, with the success of deep neural networks that are able to encode high-level semantics. Yet, while humans have the innate capability in leveraging their knowledge to decide…

Deep Convolutional Neural Networks (CNN) enforces supervised information only at the output layer, and hidden layers are trained by back propagating the prediction error from the output layer without explicit supervision. We propose a…

Distributed representations of meaning are a natural way to encode covariance relationships between words and phrases in NLP. By overcoming data sparsity problems, as well as providing information about semantic relatedness which is not…

In the context of classification problems, Deep Learning (DL) approaches represent state of art. Many DL approaches are based on variations of standard multi-layer feed-forward neural networks. These are also referred to as deep networks.…

Neuron Interpretation has gained traction in the field of interpretability, and have provided fine-grained insights into what a model learns and how language knowledge is distributed amongst its different components. However, the lack of…

This paper presents a new artificial neuron model capable of learning its receptive field in the topological domain of inputs. The model provides adaptive and differentiable local connectivity (plasticity) applicable to any domain. It…

Instruction Tuning (IT) has been proven to be an effective approach to unlock the powerful capabilities of large language models (LLMs). Recent studies indicate that excessive IT data can degrade LLMs performance, while carefully selecting…

Language and culture are deeply intertwined, yet it has been unclear how and where multilingual large language models encode culture. Here, we build on an established methodology for identifying language-specific neurons to localize and…

Deep learning has largely improved the performance of various natural language processing (NLP) tasks. However, most deep learning models are black-box machinery, and lack explicit interpretation. In this chapter, we will introduce our…