Related papers: CARE: Coherent Actionable Recourse based on Sound …

Counterfactual explanations are a widely used approach in Explainable AI, offering actionable insights into decision-making by illustrating how small changes to input data can lead to different outcomes. Despite their importance, evaluating…

A highly accurate but overconfident model is ill-suited for deployment in critical applications such as healthcare and autonomous driving. The classification outcome should reflect a high uncertainty on ambiguous in-distribution samples…

The application of deep learning in medical imaging has significantly advanced diagnostic capabilities, enhancing both accuracy and efficiency. Despite these benefits, the lack of transparency in these AI models, often termed "black boxes,"…

Building interpretable parameterizations of real-world decision-making on the basis of demonstrated behavior -- i.e. trajectories of observations and actions made by an expert maximizing some unknown reward function -- is essential for…

In this paper, we show that counterfactual explanations of confidence scores help users better understand and better trust an AI model's prediction in human-subject studies. Showing confidence scores in human-agent interaction systems can…

We address multimodal deepfake detection requiring both robustness and interpretability by proposing FakeHunter, a unified framework that combines memory guided retrieval, a structured Observation-Thought-Action reasoning loop, and adaptive…

Understanding predictions made by deep neural networks is notoriously difficult, but also crucial to their dissemination. As all machine learning based methods, they are as good as their training data, and can also capture unwanted biases.…

Counterfactual explanations elucidate algorithmic decisions by pointing to scenarios that would have led to an alternative, desired outcome. Giving insight into the model's behavior, they hint users towards possible actions and give grounds…

This paper investigates the prospects of using directive explanations to assist people in achieving recourse of machine learning decisions. Directive explanations list which specific actions an individual needs to take to achieve their…

We propose a new approach for modeling and reconciling conflicting data cleaning actions. Such conflicts arise naturally in collaborative data curation settings where multiple experts work independently and then aim to put their efforts…

Large language models (LLMs) are increasingly utilized as proxies for computational social analysis; yet, their ability to faithfully represent the "thick descriptions" (Geertz, 1973) of human communities remains a critical challenge.…

In this paper, we demonstrate the feasibility of alterfactual explanations for black box image classifiers. Traditional explanation mechanisms from the field of Counterfactual Thinking are a widely-used paradigm for Explainable Artificial…

There is a broad consensus on the importance of deep learning models in tasks involving complex data. Often, an adequate understanding of these models is required when focusing on the transparency of decisions in human-critical…

As machine learning systems increasingly inform critical decisions, the need for human-understandable explanations grows. Current evaluations of Explainable AI (XAI) often prioritize technical fidelity over cognitive accessibility which…

Counterfactual explanation (CE) is a core technique in explainable artificial intelligence (XAI), widely used to interpret model decisions and suggest actionable alternatives. This work presents a structure-aware and robustness-oriented…

Displaying confidence scores in human-AI interaction has been shown to help build trust between humans and AI systems. However, most existing research uses only the confidence score as a form of communication. As confidence scores are just…

While AI algorithms have shown remarkable success in various fields, their lack of transparency hinders their application to real-life tasks. Although explanations targeted at non-experts are necessary for user trust and human-AI…

When language models process syntactically complex sentences, do they use their representations of syntax in a manner that is consistent with the grammar of the language? We propose AlterRep, an intervention-based method to address this…

Physical and optical factors interacting with sensor characteristics create complex image degradation patterns. Despite advances in deep learning-based super-resolution, existing methods overlook the causal nature of degradation by adopting…

Linear residualization is a common practice for confounding adjustment in machine learning (ML) applications. Recently, causality-aware predictive modeling has been proposed as an alternative causality-inspired approach for adjusting for…