Related papers: Evaluating Local Explainability Metrics for Machin…
As black-box machine learning models grow in complexity and find applications in high-stakes scenarios, it is imperative to provide explanations for their predictions. Although Local Interpretable Model-agnostic Explanations (LIME) [22] is…
The number of local model-agnostic explanation techniques proposed has grown rapidly recently. One main reason is that the bar for developing new explainability techniques is low due to the lack of optimal evaluation measures. Without…
Large language models (LLMs) have demonstrated impressive capabilities in natural language processing. However, their internal mechanisms are still unclear and this lack of transparency poses unwanted risks for downstream applications.…
Explainability features are intended to provide insight into the internal mechanisms of an AI device, but there is a lack of evaluation techniques for assessing the quality of provided explanations. We propose a framework to assess and…
Large Language Models (LLMs) fine-tuned on serialized tabular data are emerging as powerful alternatives to traditional tree-based models, particularly for heterogeneous or context-rich datasets. However, their deployment in high-stakes…
The vast majority of research on explainability focuses on post-explainability rather than explainable modeling. Namely, an explanation model is derived to explain a complex black box model built with the sole purpose of achieving the…
Human-annotated labels and explanations are critical for training explainable NLP models. However, unlike human-annotated labels whose quality is easier to calibrate (e.g., with a majority vote), human-crafted free-form explanations can be…
Interpretable Machine Learning (IML) has become increasingly important in many real-world applications, such as autonomous cars and medical diagnosis, where explanations are significantly preferred to help people better understand how…
Recent advancements in machine learning have emphasized the need for transparency in model predictions, particularly as interpretability diminishes when using increasingly complex architectures. In this paper, we propose leveraging…
As the use of deep learning techniques has grown across various fields over the past decade, complaints about the opaqueness of the black-box models have increased, resulting in an increased focus on transparency in deep learning models.…
The ability to interpret Machine Learning (ML) models is becoming increasingly essential. However, despite significant progress in the field, there remains a lack of rigorous characterization regarding the innate interpretability of…
The overarching goal of Explainable AI is to develop systems that not only exhibit intelligent behaviours, but also are able to explain their rationale and reveal insights. In explainable machine learning, methods that produce a high level…
Machine learning-based systems are rapidly gaining popularity and in-line with that there has been a huge research surge in the field of explainability to ensure that machine learning models are reliable, fair, and can be held liable for…
Explainability in machine learning has become incredibly important as machine learning-powered systems become ubiquitous and both regulation and public sentiment begin to demand an understanding of how these systems make decisions. As a…
Model explainability has become an important problem in machine learning (ML) due to the increased effect that algorithmic predictions have on humans. Explanations can help users understand not only why ML models make certain predictions,…
As input data distributions evolve, the predictive performance of machine learning models tends to deteriorate. In the past, predictive performance was considered the key indicator to monitor. However, explanation aspects have come to…
Although a recent shift has been made in the field of predictive process monitoring to use models from the explainable artificial intelligence field, the evaluation still occurs mainly through performance-based metrics, thus not accounting…
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…
Local explainability methods -- those which seek to generate an explanation for each prediction -- are becoming increasingly prevalent due to the need for practitioners to rationalize their model outputs. However, comparing local…
Active learning has long been a topic of study in machine learning. However, as increasingly complex and opaque models have become standard practice, the process of active learning, too, has become more opaque. There has been little…