Related papers: Pushing the Boundaries of Interpretability: Increm…
Optimizing costly black-box functions within a constrained evaluation budget presents significant challenges in many real-world applications. Surrogate Optimization (SO) is a common resolution, yet its proprietary nature introduced by the…
In the early days of machine learning (ML), the emphasis was on developing complex algorithms to achieve best predictive performance. To understand and explain the model results, one had to rely on post hoc explainability techniques, which…
The demand for reliable AI systems has intensified the need for interpretable deep neural networks. Concept bottleneck models (CBMs) have gained attention as an effective approach by leveraging human-understandable concepts to enhance…
Black box machine learning models are currently being used for high stakes decision-making throughout society, causing problems throughout healthcare, criminal justice, and in other domains. People have hoped that creating methods for…
Many Machine Learning algorithms, such as deep neural networks, have long been criticized for being "black-boxes"-a kind of models unable to provide how it arrive at a decision without further efforts to interpret. This problem has raised…
In the context of human-in-the-loop Machine Learning applications, like Decision Support Systems, interpretability approaches should provide actionable insights without making the users wait. In this paper, we propose Accelerated…
Automatic speech recognition (ASR) outcomes serve as input for downstream tasks, substantially impacting the satisfaction level of end-users. Hence, the diagnosis and enhancement of the vulnerabilities present in the ASR model bear…
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…
Academic research and the financial industry have recently paid great attention to Machine Learning algorithms due to their power to solve complex learning tasks. In the field of firms' default prediction, however, the lack of…
The recent boom of large language models (LLMs) has re-ignited the hope that artificial intelligence (AI) systems could aid medical diagnosis. Yet despite dazzling benchmark scores, LLM assistants have yet to deliver measurable improvements…
Artificial Intelligence (AI) systems have shown good success at classifying. However, the lack of explainability is a true and significant challenge, especially in high-stakes domains, such as health and finance, where understanding is…
Although modern machine learning and deep learning methods allow for complex and in-depth data analytics, the predictive models generated by these methods are often highly complex, and lack transparency. Explainable AI (XAI) methods are…
Machine learning methods based on AdaBoost have been widely applied to various classification problems across many mission-critical applications including healthcare, law and finance. However, there is a growing concern about the unfairness…
Modern deterministic retrieval pipelines prioritize achieving state-of-the-art performance but often lack interpretability in decision-making. These models face challenges in assessing uncertainty, leading to overconfident predictions. To…
Advancements in high-throughput technologies have led to a shift from traditional hypothesis-driven methodologies to data-driven approaches. Multi-omics refers to the integrative analysis of data derived from multiple 'omes', such as…
Unlike classical lexical overlap metrics such as BLEU, most current evaluation metrics (such as BERTScore or MoverScore) are based on black-box language models such as BERT or XLM-R. They often achieve strong correlations with human…
Existing Bayesian Optimization (BO) methods typically balance exploration and exploitation to optimize costly objective functions. However, these methods often suffer from a significant one-step bias, which may lead to convergence towards…
Learned Cost Models (LCMs) have shown superior results over traditional database cost models as they can significantly improve the accuracy of cost predictions. However, LCMs still fail for some query plans, as prediction errors can be…
Interpretability, explainability and transparency are key issues to introducing Artificial Intelligence methods in many critical domains: This is important due to ethical concerns and trust issues strongly connected to reliability,…
In practice, machine learning (ML) workflows require various different steps, from data preprocessing, missing value imputation, model selection, to model tuning as well as model evaluation. Many of these steps rely on human ML experts.…