Related papers: LEx: A Framework for Operationalising Layers of Ma…

The growing application of artificial intelligence in sensitive domains has intensified the demand for systems that are not only accurate but also explainable and trustworthy. Although explainable AI (XAI) methods have proliferated, many do…

Using machine learning in high-stakes applications often requires predictions to be accompanied by explanations comprehensible to the domain user, who has ultimate responsibility for decisions and outcomes. Recently, a new framework for…

Models that generate extractive rationales (i.e., subsets of features) or natural language explanations (NLEs) for their predictions are important for explainable AI. While an extractive rationale provides a quick view of the features most…

As Large Language Models (LLMs) become increasingly integrated into high-stakes domains, there have been several approaches proposed toward generating natural language explanations. These explanations are crucial for enhancing the…

Understanding when and why to apply any given eXplainable Artificial Intelligence (XAI) technique is not a straightforward task. There is no single approach that is best suited for a given context. This paper aims to address the challenge…

Effectiveness and interpretability are two essential properties for trustworthy AI systems. Most recent studies in visual reasoning are dedicated to improving the accuracy of predicted answers, and less attention is paid to explaining the…

The field of explainable AI (XAI) has quickly become a thriving and prolific community. However, a silent, recurrent and acknowledged issue in this area is the lack of consensus regarding its terminology. In particular, each new…

Despite the increasing use of large language models (LLMs) for context-grounded tasks like summarization and question-answering, understanding what makes an LLM produce a certain response is challenging. We propose Multi-Level Explanations…

Natural language explanations (NLEs) are a special form of data annotation in which annotators identify rationales (most significant text tokens) when assigning labels to data instances, and write out explanations for the labels in natural…

Many high-performing machine learning models are not interpretable. As they are increasingly used in decision scenarios that can critically affect individuals, it is necessary to develop tools to better understand their outputs. Popular…

Learning to Reject (LtR) frameworks allow ML models to abstain from uncertain predictions and promote user trust. However, since current LtR strategies focus solely on predictive performance, they completely neglect explanation quality.…

The recent enthusiasm for artificial intelligence (AI) is due principally to advances in deep learning. Deep learning methods are remarkably accurate, but also opaque, which limits their potential use in safety-critical applications. To…

This work proposes a novel general framework, in the context of eXplainable Artificial Intelligence (XAI), to construct explanations for the behaviour of Machine Learning (ML) models in terms of middle-level features. One can isolate two…

It is a mystery which input features contribute to a neural network's output. Various explanation (feature attribution) methods are proposed in the literature to shed light on the problem. One peculiar observation is that these explanations…

The main objective of eXplainable Artificial Intelligence (XAI) is to provide effective explanations for black-box classifiers. The existing literature lists many desirable properties for explanations to be useful, but there is no consensus…

Much of explainable AI research treats explanations as a means for model inspection. Yet, this neglects findings from human psychology that describe the benefit of self-explanations in an agent's learning process. Motivated by this, we…

Effective AI governance requires structured approaches for stakeholders to access and verify AI system behavior. With the rise of large language models, Natural Language Explanations (NLEs) are now key to articulating model behavior, which…

Machine learning models achieve state-of-the-art performance across domains, yet their lack of interpretability limits safe deployment in high-stakes settings. Counterfactual explanations are widely used to provide actionable "what-if"…

Machine learning algorithms are being used in high-stakes decisions, including those in criminal justice, healthcare, credit, and employment. The research community has responded with two largely independent research fields:…

Explaining opaque Machine Learning (ML) models has become an increasingly important challenge. However, current eXplanation in AI (XAI) methods suffer several shortcomings, including insufficient abstraction, limited user interactivity, and…