相关论文: On the reliability of feature attribution methods …

Speech classification has attracted increasing attention due to its wide applications, particularly in classifying physical and mental states. However, these tasks are challenging due to the high variability in speech signals. Ensemble…

Multimodal Large Language Models (mLLMs) are often used to answer questions in structured data such as tables in Markdown, JSON, and images. While these models can often give correct answers, users also need to know where those answers come…

Diagnosing autism spectrum disorder (ASD) by identifying abnormal speech patterns from examiner-patient dialogues presents significant challenges due to the subtle and diverse manifestations of speech-related symptoms in affected…

The recent spike in certified Artificial Intelligence (AI) tools for healthcare has renewed the debate around adoption of this technology. One thread of such debate concerns Explainable AI (XAI) and its promise to render AI devices more…

Incomplete data are common in practical applications. Most predictive machine learning models do not handle missing values so they require some preprocessing. Although many algorithms are used for data imputation, we do not understand the…

Large language models (LLMs) have demonstrated impressive capabilities across a wide range of natural language processing tasks. However, their outputs often exhibit social biases, raising fairness concerns. Existing debiasing methods, such…

Word segmentation, the problem of finding word boundaries in speech, is of interest for a range of tasks. Previous papers have suggested that for sequence-to-sequence models trained on tasks such as speech translation or speech recognition,…

Attributing outputs from Large Language Models (LLMs) in adversarial settings-such as cyberattacks and disinformation campaigns-presents significant challenges that are likely to grow in importance. We approach this attribution problem from…

A long-standing question in automatic speech recognition research is how to attribute errors to the ability of a model to model the acoustics, versus its ability to leverage higher-order context (lexicon, morphology, syntax, semantics). We…

Diffusion probabilistic models have been recently used in a variety of tasks, including speech enhancement and synthesis. As a generative approach, diffusion models have been shown to be especially suitable for imputation problems, where…

Feature Learning aims to extract relevant information contained in data sets in an automated fashion. It is driving force behind the current deep learning trend, a set of methods that have had widespread empirical success. What is lacking…

Despite the widespread adoption of autoregressive language models, explainability evaluation research has predominantly focused on span infilling and masked language models. Evaluating the faithfulness of an explanation method -- how…

One principal approach for illuminating a black-box neural network is feature attribution, i.e. identifying the importance of input features for the network's prediction. The predictive information of features is recently proposed as a…

Recent speech enhancement models have shown impressive performance gains by scaling up model complexity and training data. However, the impact of dataset variability (e.g. text, language, speaker, and noise) has been underexplored.…

Large, pre-trained representation models trained using self-supervised learning have gained popularity in various fields of machine learning because they are able to extract high-quality salient features from input data. As such, they have…

In probabilistic approaches to classification and information extraction, one typically builds a statistical model of words under the assumption that future data will exhibit the same regularities as the training data. In many data sets,…

Feature attributions based on the Shapley value are popular for explaining machine learning models; however, their estimation is complex from both a theoretical and computational standpoint. We disentangle this complexity into two factors:…

Deep neural networks for classification are vulnerable to adversarial attacks, where small perturbations to input samples lead to incorrect predictions. This susceptibility, combined with the black-box nature of such networks, limits their…

The increasing success of audio foundation models across various tasks has led to a growing need for improved interpretability to understand their intricate decision-making processes better. Existing methods primarily focus on explaining…

We study how well large language models (LLMs) explain their generations through rationales -- a set of tokens extracted from the input text that reflect the decision-making process of LLMs. Specifically, we systematically study rationales…