Related papers: Consequence-aware Sequential Counterfactual Genera…

AI-driven outcomes can be challenging for end-users to understand. Explanations can address two key questions: "Why this outcome?" (factual) and "Why not another?" (counterfactual). While substantial efforts have been made to formalize…

Learning user representations based on historical behaviors lies at the core of modern recommender systems. Recent advances in sequential recommenders have convincingly demonstrated high capability in extracting effective user…

Synthetic time series are often used in practical applications to augment the historical time series dataset for better performance of machine learning algorithms, amplify the occurrence of rare events, and also create counterfactual…

Counterfactual explanations, and their associated algorithmic recourse, are typically leveraged to understand, explain, and potentially alter a prediction coming from a black-box classifier. In this paper, we propose to extend the use of…

Whenever a clinician reflects on the efficacy of a sequence of treatment decisions for a patient, they may try to identify critical time steps where, had they made different decisions, the patient's health would have improved. While recent…

Despite the widespread adoption of autoregressive language models, explainability evaluation research has predominantly focused on span infilling and masked language models. Evaluating the faithfulness of an explanation method -- how…

Counterfactual explanations are one of the prominent eXplainable Artificial Intelligence (XAI) techniques, and suggest changes to input data that could alter predictions, leading to more favourable outcomes. Existing counterfactual methods…

Counterfactual thinking describes a psychological phenomenon that people re-infer the possible results with different solutions about things that have already happened. It helps people to gain more experience from mistakes and thus to…

Counterfactual reasoning from logged data has become increasingly important for many applications such as web advertising or healthcare. In this paper, we address the problem of learning stochastic policies with continuous actions from the…

When applied in healthcare, reinforcement learning (RL) seeks to dynamically match the right interventions to subjects to maximize population benefit. However, the learned policy may disproportionately allocate efficacious actions to one…

Recent studies have shown the impressive efficacy of counterfactually augmented data (CAD) for reducing NLU models' reliance on spurious features and improving their generalizability. However, current methods still heavily rely on human…

To understand the black-box characteristics of deep networks, counterfactual explanation that deduces not only the important features of an input space but also how those features should be modified to classify input as a target class has…

Unlike traditional supervised learning, in many settings only partial feedback is available. We may only observe outcomes for the chosen actions, but not the counterfactual outcomes associated with other alternatives. Such settings…

Mammogram benign or malignant classification with only image-level labels is challenging due to the absence of lesion annotations. Motivated by the symmetric prior that the lesions on one side of breasts rarely appear in the corresponding…

Counterfactual explanation methods have recently received significant attention for explaining CNN-based image classifiers due to their ability to provide easily understandable explanations that align more closely with human reasoning.…

Counterfactual examples for an input -- perturbations that change specific features but not others -- have been shown to be useful for evaluating bias of machine learning models, e.g., against specific demographic groups. However,…

Generative models for counterfactual outcomes face two key sources of bias. Confounding bias arises when approaches fail to account for systematic differences between those who receive the intervention and those who do not. Misspecification…

We consider counterfactual explanations, the problem of minimally adjusting features in a source input instance so that it is classified as a target class under a given classifier. This has become a topic of recent interest as a way to…

In recent years, various machine and deep learning architectures have been successfully introduced to the field of predictive process analytics. Nevertheless, the inherent opacity of these algorithms poses a significant challenge for human…

Generative AI models face the challenge of hallucinations that can undermine users' trust in such systems. We approach the problem of conversational information seeking as a two-step process, where relevant passages in a corpus are…