Contrastive explanation methods go beyond transparency and address the contrastive aspect of explanations. Such explanations are emerging as an attractive option to provide actionable change to scenarios adversely impacted by classifiers' decisions. However, their extension to textual data is under-explored and there is little investigation on their vulnerabilities and limitations. This work motivates textual counterfactuals by laying the ground for a novel evaluation scheme inspired by the faithfulness of explanations. Accordingly, we extend the computation of three metrics, proximity,connectedness and stability, to textual data and we benchmark two successful contrastive methods, POLYJUICE and MiCE, on our suggested metrics. Experiments on sentiment analysis data show that the connectedness of counterfactuals to their original counterparts is not obvious in both models. More interestingly, the generated contrastive texts are more attainable with POLYJUICE which highlights the significance of latent representations in counterfactual search. Finally, we perform the first semantic adversarial attack on textual recourse methods. The results demonstrate the robustness of POLYJUICE and the role that latent input representations play in robustness and reliability.

Humans are experts in making decisions for challenging driving tasks with uncertainties. Many efforts have been made to model the decision-making process of human drivers at the behavior level. However, limited studies explain how human drivers actively make reliable sequential decisions to complete interactive driving tasks in an uncertain environment. This paper argues that human drivers intently search for actions to reduce the uncertainty of their perception of the environment, i.e., perceptual uncertainty, to a low level that allows them to make a trustworthy decision easily. This paper provides a proof of concept framework to empirically reveal that human drivers' perceptual uncertainty decreases when executing interactive tasks with uncertainties. We first introduce an explainable-artificial intelligence approach (i.e., SHapley Additive exPlanation, SHAP) to determine the salient features on which human drivers make decisions. Then, we use entropy-based measures to quantify the drivers' perceptual changes in these ranked salient features across the decision-making process, reflecting the changes in uncertainties. The validation and verification of our proposed method are conducted in the highway on-ramp merging scenario with congested traffic using the INTERACTION dataset. Experimental results support that human drivers intentionally seek information to reduce their perceptual uncertainties in the number and rank of salient features of their perception of environments to make a trustworthy decision.

Within the space of just two or three decades, artificial intelligence (AI) has left the pages of science fiction novels and become one of the cornerstone technologies of modern-day society. Success in machine learning (ML) has led to a torrent of new AI applications that are almost too numerous to count, from autonomous machines and biometrics to predictive analytics and chatbots. One emerging application of AI in recent years has been conversational intelligence (CI). While automated chatbots and virtual assistants are concerned with human-to-computer interaction, CI aims to explore human-to-human interaction in greater detail. The potential to monitor and extract data from human conversations, including tone, sentiment and context, has seemingly limitless potential.

Most research on natural language processing treats bias as an absolute concept: Based on a (probably complex) algorithmic analysis, a sentence, an article, or a text is classified as biased or not. Given the fact that for humans the question of whether a text is biased can be difficult to answer or is answered contradictory, we ask whether an "absolute bias classification" is a promising goal at all. We see the problem not in the complexity of interpreting language phenomena but in the diversity of sociocultural backgrounds of the readers, which cannot be handled uniformly: To decide whether a text has crossed the proverbial line between non-biased and biased is subjective. By asking "Is text X more [less, equally] biased than text Y?" we propose to analyze a simpler problem, which, by its construction, is rather independent of standpoints, views, or sociocultural aspects. In such a model, bias becomes a preference relation that induces a partial ordering from least biased to most biased texts without requiring a decision on where to draw the line. A prerequisite for this kind of bias model is the ability of humans to perceive relative bias differences in the first place. In our research, we selected a specific type of bias in argumentation, the stance bias, and designed a crowdsourcing study showing that differences in stance bias are perceptible when (light) support is provided through training or visual aid.

Being able to provide counterfactual interventions - sequences of actions we would have had to take for a desirable outcome to happen - is essential to explain how to change an unfavourable decision by a black-box machine learning model (e.g., being denied a loan request). Existing solutions have mainly focused on generating feasible interventions without providing explanations on their rationale. Moreover, they need to solve a separate optimization problem for each user. In this paper, we take a different approach and learn a program that outputs a sequence of explainable counterfactual actions given a user description and a causal graph. We leverage program synthesis techniques, reinforcement learning coupled with Monte Carlo Tree Search for efficient exploration, and rule learning to extract explanations for each recommended action. An experimental evaluation on synthetic and real-world datasets shows how our approach generates effective interventions by making orders of magnitude fewer queries to the black-box classifier with respect to existing solutions, with the additional benefit of complementing them with interpretable explanations.

Counterfactual explanations have substantially increased in popularity in the past few years as a useful human-centric way of understanding individual black-box model predictions. While several properties desired of high-quality counterfactuals have been identified in the literature, three crucial concerns: the speed of explanation generation, robustness/sensitivity and succinctness of explanations (sparsity) have been relatively unexplored. In this paper, we present FASTER-CE: a novel set of algorithms to generate fast, sparse, and robust counterfactual explanations. The key idea is to efficiently find promising search directions for counterfactuals in a latent space that is specified via an autoencoder. These directions are determined based on gradients with respect to each of the original input features as well as of the target, as estimated in the latent space. The ability to quickly examine combinations of the most promising gradient directions as well as to incorporate additional user-defined constraints allows us to generate multiple counterfactual explanations that are sparse, realistic, and robust to input manipulations. Through experiments on three datasets of varied complexities, we show that FASTER-CE is not only much faster than other state of the art methods for generating multiple explanations but also is significantly superior when considering a larger set of desirable (and often conflicting) properties. Specifically we present results across multiple performance metrics: sparsity, proximity, validity, speed of generation, and the robustness of explanations, to highlight the capabilities of the FASTER-CE family.

Saliency map explanation for an ECG exam that is predicted to be low-quality. Red highlights the part of the image most important to the model's prediction, while purple indicates the least important area. Ana Lucic, a PhD candidate at the Information Retrieval Lab (IRLab) of the Informatics Institute of UvA, has developed a framework for explaining predictions of machine learning models that could improve heart examinations for underserved communities. The work of Lucic is part of the subfield of AI, called explainable artificial intelligence (XAI). "We need explainable AI", says Lucic, "because machine learning models are often difficult to interpret. They have complex architectures and large numbers of parameters, so it's not clear how the input contributes to the output."

Artificial Intelligence (AI) is one of the approaches that has been proposed to analyze the collected data (e.g., vibration signals) providing a diagnosis of the asset's operating condition. It is known that models trained with labeled data (supervised) achieve excellent results, but two main problems make their application in production processes difficult: (i) impossibility or long time to obtain a sample of all operational conditions (since faults seldom happen) and (ii) high cost of experts to label all acquired data. Another limitating factor for the applicability of AI approaches in this context is the lack of interpretability of the models (black-boxes), which reduces the confidence of the diagnosis and trust/adoption from users. To overcome these problems, a new generic and interpretable approach for classifying faults in rotating machinery based on transfer learning from augmented synthetic data to real rotating machinery is here proposed, namelly FaultD-XAI (Fault Diagnosis using eXplainable AI). To provide scalability using transfer learning, synthetic vibration signals are created mimicking the characteristic behavior of failures in operation. The application of Gradient-weighted Class Activation Mapping (Grad-CAM) with 1D Convolutional Neural Network (1D CNN) allows the interpretation of results, supporting the user in decision making and increasing diagnostic confidence. The proposed approach not only obtained promising diagnostic performance, but was also able to learn characteristics used by experts to identify conditions in a source domain and apply them in another target domain. The experimental results suggest a promising approach on exploiting transfer learning, synthetic data and explainable artificial intelligence for fault diagnosis. Lastly, to guarantee reproducibility and foster research in the field, the developed dataset is made publicly available.

Artificial Intelligence (AI) increasingly shows its potential to outperform predicate logic algorithms and human control alike. In automatically deriving a system model, AI algorithms learn relations in data that are not detectable for humans. This great strength, however, also makes use of AI methods dubious. The more complex a model, the more difficult it is for a human to understand the reasoning for the decisions. As currently, fully automated AI algorithms are sparse, every algorithm has to provide a reasoning for human operators. For data engineers, metrics such as accuracy and sensitivity are sufficient. However, if models are interacting with non-experts, explanations have to be understandable. This work provides an extensive survey of literature on this topic, which, to a large part, consists of other surveys. The findings are mapped to ways of explaining decisions and reasons for explaining decisions. It shows that the heterogeneity of reasons and methods of and for explainability lead to individual explanatory frameworks.

There is no instruction for a decision-making process. However, important decisions are usually made by analyzing tons of data to find the optimal way to solve a problem. That's where we truly rely on logic and deduction. That's why surgeons dig into anamnesis, or businesses gather key persons to see a bigger picture before making a turn. Relying on AI decision-making can significantly reduce the time spent on research and data gathering.