Related papers: An Interpretability-Guided Framework for Responsib…
A growing number of approaches exist to generate explanations for image classification. However, few of these approaches are subjected to human-subject evaluations, partly because it is challenging to design controlled experiments with…
High-fidelity generative models are increasingly needed in privacy-sensitive scenarios, where access to data is severely restricted due to regulatory and copyright constraints. This scarcity hampers model development--ironically, in…
Training models on synthetic data has emerged as an increasingly important strategy for improving the performance of generative AI. This approach is particularly helpful for large multimodal models (LMMs) due to the relative scarcity of…
The generation of explanation graphs is a significant task that aims to produce explanation graphs in response to user input, revealing the internal reasoning process. This task is challenging due to the significant discrepancy between…
Synthetic data is emerging as a cost-effective solution necessary to meet the increasing data demands of AI development, created either from existing knowledge or derived from real data. The traditional classification of synthetic data…
Explainable artificial intelligence (XAI) enables data-driven understanding of factor associations with response variables, yet communicating XAI outputs to laypersons remains challenging, hindering trust in AI-based predictions. Large…
Measuring the value of individual samples is critical for many data-driven tasks, e.g., the training of a deep learning model. Recent literature witnesses the substantial efforts in developing data valuation methods. The primary data…
Predictive process analytics focuses on predicting the future states of running instances of a business process. While advanced machine learning techniques have been used to increase accuracy of predictions, the resulting predictive models…
Natural language explanations (NLEs) are commonly used to provide plausible free-text explanations of a model's reasoning about its predictions. However, recent work has questioned their faithfulness, as they may not accurately reflect the…
The rapid advancement of AI and computer vision has significantly increased the demand for high-quality annotated datasets, particularly for semantic segmentation. However, creating such datasets is resource-intensive, requiring substantial…
Shapley additive explanations (SHAP) are widely recognised as computationally intractable for neural networks, since they induce an exponential search space over the input features. In this work, we take a first step towards scaling exact…
Suicidal ideation detection is a vital research area that holds great potential for improving mental health support systems. However, the sensitivity surrounding suicide-related data poses challenges in accessing large-scale, annotated…
Human use language not just to convey information but also to express their inner feelings and mental states. In this work, we adapt the state-of-the-art language generation models to generate affective (emotional) text. We posit a model…
Unsupervised learning allows us to leverage unlabelled data, which has become abundantly available, and to create embeddings that are usable on a variety of downstream tasks. However, the typical lack of interpretability of unsupervised…
Explainable AI is an emerging field providing solutions for acquiring insights into automated systems' rationale. It has been put on the AI map by suggesting ways to tackle key ethical and societal issues. Existing explanation techniques…
Neural networks (NNs), with their powerful nonlinear mapping and end-to-end capabilities, are widely applied in mechanical intelligent fault diagnosis (IFD). However, as typical black-box models, they pose challenges in understanding their…
Recent studies have examined the computational complexity of computing Shapley additive explanations (also known as SHAP) across various models and distributions, revealing their tractability or intractability in different settings.…
Most methods for explaining black-box classifiers (e.g. on tabular data, images, or time series) rely on measuring the impact that removing/perturbing features has on the model output. This forces the explanation language to match the…
Although social media platforms are a prominent arena for users to engage in interpersonal discussions and express opinions, the facade and anonymity offered by social media may allow users to spew hate speech and offensive content. Given…
Recent generative data augmentation methods conditioned on both image and text prompts struggle to balance between fidelity and diversity, as it is challenging to preserve essential image details while aligning with varied text prompts.…