相关论文: c-Eval: A Unified Metric to Evaluate Feature-based…

As the application of deep neural networks proliferates in numerous areas such as medical imaging, video surveillance, and self driving cars, the need for explaining the decisions of these models has become a hot research topic, both at the…

While deep neural networks have achieved remarkable performance, they tend to lack transparency in prediction. The pursuit of greater interpretability in neural networks often results in a degradation of their original performance. Some…

We evaluated whether model explanations could efficiently detect bias in image classification by highlighting discriminating features, thereby removing the reliance on sensitive attributes for fairness calculations. To this end, we…

Large proprietary language models exhibit strong causal reasoning abilities that smaller open-source models struggle to replicate. We introduce a novel framework for distilling causal explanations that transfers causal reasoning skills from…

Deep learning models in computer vision have made remarkable progress, but their lack of transparency and interpretability remains a challenge. The development of explainable AI can enhance the understanding and performance of these models.…

Studies have been conducted to prevent specific concepts from being generated from pretrained text-to-image generative models, achieving concept erasure in various ways. However, the performance evaluation of these studies is still largely…

The interpretability of prediction mechanisms with respect to the underlying prediction problem is often unclear. While several studies have focused on developing prediction models with meaningful parameters, the causal relationships…

Model explanations based on pure observational data cannot compute the effects of features reliably, due to their inability to estimate how each factor alteration could affect the rest. We argue that explanations should be based on the…

We tackle the problem of computing counterfactual explanations -- minimal changes to the features that flip an undesirable model prediction. We propose a solution to this question for linear Support Vector Machine (SVMs) models. Moreover,…

Estimating causal effects from observational data is challenging, especially in the presence of latent confounders. Much work has been done on addressing this challenge, but most of the existing research ignores the bias introduced by the…

While local explanations for AI models can offer insights into individual predictions, such as feature importance, they are plagued by issues like instability. The unreliability of feature weights, often skewed due to poorly calibrated ML…

Calibration strengthens the trustworthiness of black-box models by producing better accurate confidence estimates on given examples. However, little is known about if model explanations can help confidence calibration. Intuitively, humans…

Automatic evaluation metrics hold a fundamental importance in the development and fine-grained analysis of captioning systems. While current evaluation metrics tend to achieve an acceptable correlation with human judgements at the system…

Despite their high accuracies, modern complex image classifiers cannot be trusted for sensitive tasks due to their unknown decision-making process and potential biases. Counterfactual explanations are very effective in providing…

As machine learning models are increasingly deployed in safety-critical domains, visual explanation techniques have become essential tools for supporting transparency. In this work, we reveal a new class of attacks that compromise model…

Feature-importance methods show promise in transforming machine learning models from predictive engines into tools for scientific discovery. However, due to data sampling and algorithmic stochasticity, expressive models can be unstable,…

Feature selection is an important but challenging task in causal inference for obtaining unbiased estimates of causal quantities. Properly selected features in causal inference not only significantly reduce the time required to implement a…

Text-image generation has advanced rapidly, but assessing whether outputs truly capture the objects, attributes, and relations described in prompts remains a central challenge. Evaluation in this space relies heavily on automated metrics,…

We introduce a conditional generative model for learning to disentangle the hidden factors of variation within a set of labeled observations, and separate them into complementary codes. One code summarizes the specified factors of variation…

Feature attribution methods are widely used for explaining image-based predictions, as they provide feature-level insights that can be intuitively visualized. However, such explanations often vary in their robustness and may fail to…