相关论文: Do Explanations make VQA Models more Predictable t…

Recent work has demonstrated the promise of combining local explanations with active learning for understanding and supervising black-box models. Here we show that, under specific conditions, these algorithms may misrepresent the quality of…

It is commonly believed that increasing the interpretability of a machine learning model may decrease its predictive power. However, inspecting input-output relationships of those models using visual analytics, while treating them as…

Answering open-ended questions is an essential capability for any intelligent agent. One of the most interesting recent open-ended question answering challenges is Visual Question Answering (VQA) which attempts to evaluate a system's visual…

We examine how users perceive the limitations of an AI system when it encounters a task that it cannot perform perfectly and whether providing explanations alongside its answers aids users in constructing an appropriate mental model of the…

With machine learning models being increasingly used to aid decision making even in high-stakes domains, there has been a growing interest in developing interpretable models. Although many supposedly interpretable models have been proposed,…

Recommender systems are central to digital platforms, yet they face a fundamental trade-off between accuracy and explainability. Black-box models achieve strong performance but lack interpretability needed for trust and adoption. Existing…

Artificial neural networks are often very complex and too deep for a human to understand. As a result, they are usually referred to as black boxes. For a lot of real-world problems, the underlying pattern itself is very complicated, such…

Explaining deep learning models is essential for clinical integration of medical image analysis systems. A good explanation highlights if a model depends on spurious features that undermines generalization and harms a subset of patients or,…

Artificial Intelligence (AI) has continued to achieve tremendous success in recent times. However, the decision logic of these frameworks is often not transparent, making it difficult for stakeholders to understand, interpret or explain…

The predominant approach to visual question answering (VQA) relies on encoding the image and question with a "black-box" neural encoder and decoding a single token as the answer like "yes" or "no". Despite this approach's strong…

Self-driving cars increasingly rely on deep neural networks to achieve human-like driving. The opacity of such black-box planners makes it challenging for the human behind the wheel to accurately anticipate when they will fail, with…

Black box systems for automated decision making, often based on machine learning over (big) data, map a user's features into a class or a score without exposing the reasons why. This is problematic not only for lack of transparency, but…

Recent work on interpretability in machine learning and AI has focused on the building of simplified models that approximate the true criteria used to make decisions. These models are a useful pedagogical device for teaching trained…

Explainability techniques for data-driven predictive models based on artificial intelligence and machine learning algorithms allow us to better understand the operation of such systems and help to hold them accountable. New transparency…

We are used to the availability of big data generated in nearly all fields of science as a consequence of technological progress. However, the analysis of such data possess vast challenges. One of these relates to the explainability of…

This paper provides empirical concerns about post-hoc explanations of black-box ML models, one of the major trends in AI explainability (XAI), by showing its lack of interpretability and societal consequences. Using a representative…

Evaluating the quality of explanations in Explainable Artificial Intelligence (XAI) is to this day a challenging problem, with ongoing debate in the research community. While some advocate for establishing standardized offline metrics,…

Modern AI systems frequently rely on opaque black-box models, most notably Deep Neural Networks, whose performance stems from complex architectures with millions of learned parameters. While powerful, their complexity poses a major…

Explainable artificial intelligence and interpretable machine learning are research domains growing in importance. Yet, the underlying concepts remain somewhat elusive and lack generally agreed definitions. While recent inspiration from…

In the era of Big Knowledge Graphs, Question Answering (QA) systems have reached a milestone in their performance and feasibility. However, their applicability, particularly in specific domains such as the biomedical domain, has not gained…