Zobrazeno 1 - 10
of 171
pro vyhledávání: '"Mac Namee, Brian"'
In this study, we aim to reduce generation latency for Named Entity Recognition (NER) with Large Language Models (LLMs). The main cause of high latency in LLMs is the sequential decoding process, which autoregressively generates all labels and mentio
Externí odkaz:
http://arxiv.org/abs/2402.04838
In machine learning systems, bias mitigation approaches aim to make outcomes fairer across privileged and unprivileged groups. Bias mitigation methods work in different ways and have known "waterfall" effects, e.g., mitigating bias at one place may m
Externí odkaz:
http://arxiv.org/abs/2312.00765
eXplanation Based Learning (XBL) is an interactive learning approach that provides a transparent method of training deep learning models by interacting with their explanations. XBL augments loss functions to penalize a model based on deviation of its
Externí odkaz:
http://arxiv.org/abs/2309.05548
Medical image classification models are frequently trained using training datasets derived from multiple data sources. While leveraging multiple data sources is crucial for achieving model generalization, it is important to acknowledge that the diver
Externí odkaz:
http://arxiv.org/abs/2308.01119
eXplanation Based Learning (XBL) is a form of Interactive Machine Learning (IML) that provides a model refining approach via user feedback collected on model explanations. Although the interactivity of XBL promotes model transparency, XBL requires a
Externí odkaz:
http://arxiv.org/abs/2307.06026
Autor:
Hagos, Misgina Tsighe, Belton, Niamh, Killeen, Ronan P., Curran, Kathleen M., Mac Namee, Brian
Alzheimer's Disease (AD) is a progressive disease preceded by Mild Cognitive Impairment (MCI). Early detection of AD is crucial for making treatment decisions. However, most of the literature on computer-assisted detection of AD focuses on classifyin
Externí odkaz:
http://arxiv.org/abs/2304.07097
Much of named entity recognition (NER) research focuses on developing dataset-specific models based on data from the domain of interest, and a limited set of related entity types. This is frustrating as each new dataset requires a new model to be tra
Externí odkaz:
http://arxiv.org/abs/2211.14838
Identifying spurious correlations learned by a trained model is at the core of refining a trained model and building a trustworthy model. We present a simple method to identify spurious correlations that have been learned by a model trained for image
Externí odkaz:
http://arxiv.org/abs/2211.08285
Current methods for prompt learning in zeroshot scenarios widely rely on a development set with sufficient human-annotated data to select the best-performing prompt template a posteriori. This is not ideal because in a realworld zero-shot scenario of
Externí odkaz:
http://arxiv.org/abs/2209.15206
Explanatory Interactive Learning (XIL) collects user feedback on visual model explanations to implement a Human-in-the-Loop (HITL) based interactive learning scenario. Different user feedback types will have different impacts on user experience and t
Externí odkaz:
http://arxiv.org/abs/2209.12476