Related papers: Capability Localization: Capabilities Can be Local…

A fundamental advantage of neural models for NLP is their ability to learn representations from scratch. However, in practice this often means ignoring existing external linguistic resources, e.g., WordNet or domain specific ontologies such…

Convolutional neural networks use pooling and other downscaling operations to maintain translational invariance for detection of features, but in their architecture they do not explicitly maintain a representation of the locations of the…

Pre-trained language models (PLMs) contain vast amounts of factual knowledge, but how the knowledge is stored in the parameters remains unclear. This paper delves into the complex task of understanding how factual knowledge is stored in…

Overparameterized deep networks that generalize well have been key to the dramatic success of deep learning in recent years. The reasons for their remarkable ability to generalize are not well understood yet. When class labels in the…

Multilingual language models (MLLMs) have demonstrated remarkable abilities to transfer knowledge across languages, despite being trained without explicit cross-lingual supervision. We analyze the parameter spaces of three MLLMs to study…

In large language models (LLMs), certain \emph{neurons} can store distinct pieces of knowledge learned during pretraining. While factual knowledge typically appears as a combination of \emph{relations} and \emph{entities}, it remains…

Despite their outstanding performance, large language models (LLMs) suffer notorious flaws related to their preference for simple, surface-level textual relations over full semantic complexity of the problem. This proposal investigates a…

The human brain can effectively learn a new task from a small number of samples, which indicate that the brain can transfer its prior knowledge to solve tasks in different domains. This function is analogous to transfer learning (TL) in the…

Large language models (LLMs) exhibit social biases that reinforce harmful stereotypes, limiting their safe deployment. Most existing debiasing methods adopt a suppressive paradigm by modifying parameters, prompts, or neurons associated with…

Relational learning deals with data that are characterized by relational structures. An important task is collective classification, which is to jointly classify networked objects. While it holds a great promise to produce a better accuracy…

With the widespread adoption of large language models (LLMs), understanding their personality representation mechanisms has become critical. As a novel paradigm in Personality Editing, most existing methods employ neuron-editing to locate…

While a lot of work has been done in understanding representations learned within deep NLP models and what knowledge they capture, little attention has been paid towards individual neurons. We present a technique called as Linguistic…

Generative large language models(LLMs) are proficient in solving general problems but often struggle to handle domain-specific tasks. This is because most of domain-specific tasks, such as personalized recommendation, rely on task-related…

Natural language is compositional; the meaning of a sentence is a function of the meaning of its parts. This property allows humans to create and interpret novel sentences, generalizing robustly outside their prior experience. Neural…

Brain localization, which describes the association between specific regions of the brain and their corresponding functions, is widely accepted in the field of cognitive science as an objective fact. Today's large language models (LLMs)…

Neurons process information in ways that depend on their cell type, connectivity, and the brain region in which they are embedded. However, inferring these factors from neural activity remains a significant challenge. To build…

Despite the recent success of Graph Neural Networks (GNNs), training GNNs on large graphs remains challenging. The limited resource capacities of the existing servers, the dependency between nodes in a graph, and the privacy concern due to…

Knowledge editing aims to update outdated information in Large Language Models (LLMs). A representative line of study is locate-then-edit methods, which typically employ causal tracing to identify the modules responsible for recalling…

In existing image classification systems that use deep neural networks, the knowledge needed for image classification is implicitly stored in model parameters. If users want to update this knowledge, then they need to fine-tune the model…

Neural networks are very powerful learning systems, but they do not readily generalize from one task to the other. This is partly due to the fact that they do not learn in a compositional way, that is, by discovering skills that are shared…