相关论文: Evaluating Post-hoc Explanations of the Transforme…

Model interpretability is a requirement in many applications in which crucial decisions are made by users relying on a model's outputs. The recent movement for "algorithmic fairness" also stipulates explainability, and therefore…

Code language models excel on code intelligence tasks, yet their internal interpretability is underexplored. Existing neuron interpretability techniques from NLP are suboptimal for source code due to programming languages formal,…

As machine learning becomes increasingly integral to autonomous decision-making processes involving human interaction, the necessity of comprehending the model's outputs through conversational means increases. Most recently, foundation…

In this work, we propose a methodology for investigating the use of semantic attention to enhance the explainability of Graph Neural Network (GNN)-based models. Graph Deep Learning (GDL) has emerged as a promising field for tasks like scene…

Motivation: Deep learning architectures have recently demonstrated their power in predicting DNA- and RNA-binding specificities. Existing methods fall into three classes: Some are based on Convolutional Neural Networks (CNNs), others use…

Neural network interpretability is a vital component for applications across a wide variety of domains. In such cases it is often useful to analyze a network which has already been trained for its specific purpose. In this work, we develop…

Convolutional neural networks (CNNs) have shown exceptional performance for a range of medical imaging tasks. However, conventional CNNs are not able to explain their reasoning process, therefore limiting their adoption in clinical…

Genetic programming (GP) has the potential to generate explainable results, especially when used for dimensionality reduction. In this research, we investigate the potential of leveraging eXplainable AI (XAI) and large language models…

We explore why deep convolutional neural networks (CNNs) with small two-dimensional kernels, primarily used for modeling spatial relations in images, are also effective in speech recognition. We analyze the representations learned by deep…

A central challenge in neuroscience is to understand neural computations and circuit mechanisms that underlie the encoding of ethologically relevant, natural stimuli. In multilayered neural circuits, nonlinear processes such as synaptic…

Given the increasingly prominent role NLP models (will) play in our lives, it is important for human expectations of model behavior to align with actual model behavior. Using Natural Language Inference (NLI) as a case study, we investigate…

Recent advancements in large language models (LLMs) have shown promising results in multilingual translation even with limited bilingual supervision. The major challenges are catastrophic forgetting and parameter interference for finetuning…

This work builds together two popular blocks of neural architecture, namely convolutional layers and Transformers, for large language models (LLMs). Non-causal conformers are used ubiquitously in automatic speech recognition. This work aims…

Effective decision-making on networks often relies on learning from graph-structured data, where Graph Neural Networks (GNNs) play a central role, but they take efforts to configure and tune. In this demo, we propose LLMNet, showing how to…

Graph Neural Networks (GNNs) are deep learning models that take graph data as inputs, and they are applied to various tasks such as traffic prediction and molecular property prediction. However, owing to the complexity of the GNNs, it has…

Graphs are ubiquitous in many applications, such as social networks, knowledge graphs, smart grids, etc.. Graph neural networks (GNN) are the current state-of-the-art for these applications, and yet remain obscure to humans. Explaining the…

While neural networks have acted as a strong unifying force in the design of modern AI systems, the neural network architectures themselves remain highly heterogeneous due to the variety of tasks to be solved. In this chapter, we explore…

Large language models (LLMs) have demonstrated remarkable capabilities across various domains, yet their application to relational deep learning (RDL) remains underexplored. Existing approaches adapt LLMs by traversing relational links…

Transfer learning with large pretrained transformer-based language models like BERT has become a dominating approach for most NLP tasks. Simply fine-tuning those large language models on downstream tasks or combining it with task-specific…

Convolutional neural networks (CNN) have improved speech recognition performance greatly by exploiting localized time-frequency patterns. But these patterns are assumed to appear in symmetric and rigid kernels by the conventional CNN…