Research Papers

Invisible Users: Uncovering End-Users' Requirements for Explainable AI via Explanation Forms and Goals

Weina Jin, Jianyu Fan, Diane Gromala +2

Non-technical end-users are silent and invisible users of the state-of-the-art explainable artificial intelligence (XAI) technologies. Their demands and requirements for AI explainability are not incorporated into the design and evaluation of XAI techniques, which are developed to explain the rationales of AI decisions to end-users and assist their critical decisions. This makes XAI techniques ineffective or even harmful in high-stakes applications, such as healthcare, criminal justice, finance, and autonomous driving systems. To systematically understand end-users' requirements to support the technical development of XAI, we conducted the EUCA user study with 32 layperson participants in four AI-assisted critical tasks. The study identified comprehensive user requirements for feature-, example-, and rule-based XAI techniques (manifested by the end-user-friendly explanation forms) and XAI evaluation objectives (manifested by the explanation goals), which were shown to be helpful to directly inspire the proposal of new XAI algorithms and evaluation metrics. The EUCA study findings, the identified explanation forms and goals for technical specification, and the EUCA study dataset support the design and evaluation of end-user-centered XAI techniques for accessible, safe, and accountable AI.

Many visualizations have been developed for explainable AI (XAI), but they often require further reasoning by users to interpret. Investigating XAI for high-stakes medical diagnosis, we propose improving domain alignment with diagrammatic and abductive reasoning to reduce the interpretability gap. We developed DiagramNet to predict cardiac diagnoses from heart auscultation, select the best-fitting hypothesis based on criteria evaluation, and explain with clinically-relevant murmur diagrams. The ante-hoc interpretable model leverages domain-relevant ontology, representation, and reasoning process to increase trust in expert users. In modeling studies, we found that DiagramNet not only provides faithful murmur shape explanations, but also has better performance than baseline models. We demonstrate the interpretability and trustworthiness of diagrammatic, abductive explanations in a qualitative user study with medical students, showing that clinically-relevant, diagrammatic explanations are preferred over technical saliency map explanations. This work contributes insights into providing domain-aligned explanations for user-centric XAI in complex domains.

Deep visual models have widespread applications in high-stake domains. Hence, their black-box nature is currently attracting a large interest of the research community. We present the first survey in Explainable AI that focuses on the methods and metrics for interpreting deep visual models. Covering the landmark contributions along the state-of-the-art, we not only provide a taxonomic organization of the existing techniques, but also excavate a range of evaluation metrics and collate them as measures of different properties of model explanations. Along the insightful discussion on the current trends, we also discuss the challenges and future avenues for this research direction.

Interactive Artificial Intelligence (AI) agents are becoming increasingly prevalent in society. However, application of such systems without understanding them can be problematic. Black-box AI systems can lead to liability and accountability issues when they produce an incorrect decision. Explainable AI (XAI) seeks to bridge the knowledge gap, between developers and end-users, by offering insights into how an AI algorithm functions. Many modern algorithms focus on making the AI model "transparent", i.e. unveil the inherent functionality of the agent in a simpler format. However, these approaches do not cater to end-users of these systems, as users may not possess the requisite knowledge to understand these explanations in a reasonable amount of time. Therefore, to be able to develop suitable XAI methods, we need to understand the factors which influence subjective perception and objective usability. In this paper, we present a novel user-study which studies four differing XAI modalities commonly employed in prior work for explaining AI behavior, i.e. Decision Trees, Text, Programs. We study these XAI modalities in the context of explaining the actions of a self-driving car on a highway, as driving is an easily understandable real-world task and self-driving cars is a keen area of interest within the AI community. Our findings highlight internal consistency issues wherein participants perceived language explanations to be significantly more usable, however participants were better able to objectively understand the decision making process of the car through a decision tree explanation. Our work also provides further evidence of importance of integrating user-specific and situational criteria into the design of XAI systems. Our findings show that factors such as computer science experience, and watching the car succeed or fail can impact the perception and usefulness of the explanation.

Machine learning (ML) on graph-structured data has recently received deepened interest in the context of intrusion detection in the cybersecurity domain. Due to the increasing amounts of data generated by monitoring tools as well as more and more sophisticated attacks, these ML methods are gaining traction. Knowledge graphs and their corresponding learning techniques such as Graph Neural Networks (GNNs) with their ability to seamlessly integrate data from multiple domains using human-understandable vocabularies, are finding application in the cybersecurity domain. However, similar to other connectionist models, GNNs are lacking transparency in their decision making. This is especially important as there tend to be a high number of false positive alerts in the cybersecurity domain, such that triage needs to be done by domain experts, requiring a lot of man power. Therefore, we are addressing Explainable AI (XAI) for GNNs to enhance trust management by exploring combining symbolic and sub-symbolic methods in the area of cybersecurity that incorporate domain knowledge. We experimented with this approach by generating explanations in an industrial demonstrator system. The proposed method is shown to produce intuitive explanations for alerts for a diverse range of scenarios. Not only do the explanations provide deeper insights into the alerts, but they also lead to a reduction of false positive alerts by 66% and by 93% when including the fidelity metric.

Atomist or Holist? A Diagnosis and Vision for More Productive Interdisciplinary AI Ethics Dialogue

Travis Greene, Amit Dhurandhar, Galit Shmueli

In response to growing recognition of the social impact of new AI-based technologies, major AI and ML conferences and journals now encourage or require papers to include ethics impact statements and undergo ethics reviews. This move has sparked heated debate concerning the role of ethics in AI research, at times devolving into name-calling and threats of "cancellation." We diagnose this conflict as one between atomist and holist ideologies. Among other things, atomists believe facts are and should be kept separate from values, while holists believe facts and values are and should be inextricable from one another. With the goal of reducing disciplinary polarization, we draw on numerous philosophical and historical sources to describe each ideology's core beliefs and assumptions. Finally, we call on atomists and holists within the ever-expanding data science community to exhibit greater empathy during ethical disagreements and propose four targeted strategies to ensure AI research benefits society.

Explanation mechanisms from the field of Counterfactual Thinking are a widely-used paradigm for Explainable Artificial Intelligence (XAI), as they follow a natural way of reasoning that humans are familiar with. However, all common approaches from this field are based on communicating information about features or characteristics that are especially important for an AI's decision. We argue that in order to fully understand a decision, not only knowledge about relevant features is needed, but that the awareness of irrelevant information also highly contributes to the creation of a user's mental model of an AI system. Therefore, we introduce a new way of explaining AI systems. Our approach, which we call Alterfactual Explanations, is based on showing an alternative reality where irrelevant features of an AI's input are altered. By doing so, the user directly sees which characteristics of the input data can change arbitrarily without influencing the AI's decision. We evaluate our approach in an extensive user study, revealing that it is able to significantly contribute to the participants' understanding of an AI. We show that alterfactual explanations are suited to convey an understanding of different aspects of the AI's reasoning than established counterfactual explanation methods.

Machine Learning has become an integral part of engineering design and decision making in several domains, including sports. Deep Neural Networks (DNNs) have been the state-of-the-art methods for predicting outcomes of professional sports events. However, apart from getting highly accurate predictions on these sports events outcomes, it is necessary to answer questions such as "Why did the model predict that Team A would win Match X against Team B?" DNNs are inherently black-box in nature. Therefore, it is required to provide high-quality interpretable, and understandable explanations for a model's prediction in sports. This paper explores a two-phased Explainable Artificial Intelligence(XAI) approach to predict outcomes of matches in the Brazilian volleyball League (SuperLiga). In the first phase, we directly use the interpretable rule-based ML models that provide a global understanding of the model's behaviors based on Boolean Rule Column Generation (BRCG; extracts simple AND-OR classification rules) and Logistic Regression (LogReg; allows to estimate the feature importance scores). In the second phase, we construct non-linear models such as Support Vector Machine (SVM) and Deep Neural Network (DNN) to obtain predictive performance on the volleyball matches' outcomes. We construct the "post-hoc" explanations for each data instance using ProtoDash, a method that finds prototypes in the training dataset that are most similar to the test instance, and SHAP, a method that estimates the contribution of each feature on the model's prediction. We evaluate the SHAP explanations using the faithfulness metric. Our results demonstrate the effectiveness of the explanations for the model's predictions.

Neural Networks are ubiquitous in high energy physics research. However, these highly nonlinear parameterized functions are treated as \textit{black boxes}- whose inner workings to convey information and build the desired input-output relationship are often intractable. Explainable AI (xAI) methods can be useful in determining a neural model's relationship with data toward making it \textit{interpretable} by establishing a quantitative and tractable relationship between the input and the model's output. In this letter of interest, we explore the potential of using xAI methods in the context of problems in high energy physics.

Towards Implementing Responsible AI

Conrad Sanderson, Qinghua Lu, David Douglas +3

As the deployment of artificial intelligence (AI) is changing many fields and industries, there are concerns about AI systems making decisions and recommendations without adequately considering various ethical aspects, such as accountability, reliability, transparency, explainability, contestability, privacy, and fairness. While many sets of AI ethics principles have been recently proposed that acknowledge these concerns, such principles are high-level and do not provide tangible advice on how to develop ethical and responsible AI systems. To gain insight on the possible implementation of the principles, we conducted an empirical investigation involving semi-structured interviews with a cohort of AI practitioners. The salient findings cover four aspects of AI system design and development, adapting processes used in software engineering: (i) high-level view, (ii) requirements engineering, (iii) design and implementation, (iv) deployment and operation.

Incorporating interdisciplinary perspectives is seen as an essential step towards enhancing artificial intelligence (AI) ethics. In this regard, the field of arts is perceived to play a key role in elucidating diverse historical and cultural narratives, serving as a bridge across research communities. Most of the works that examine the interplay between the field of arts and AI ethics concern digital artworks, largely exploring the potential of computational tools in being able to surface biases in AI systems. In this paper, we investigate a complementary direction--that of uncovering the unique socio-cultural perspectives embedded in human-made art, which in turn, can be valuable in expanding the horizon of AI ethics. Through semi-structured interviews across sixteen artists, art scholars, and researchers of diverse Indian art forms like music, sculpture, painting, floor drawings, dance, etc., we explore how {\it non-Western} ethical abstractions, methods of learning, and participatory practices observed in Indian arts, one of the most ancient yet perpetual and influential art traditions, can shed light on aspects related to ethical AI systems. Through a case study concerning the Indian dance system (i.e. the {\it `Natyashastra'}), we analyze potential pathways towards enhancing ethics in AI systems. Insights from our study outline the need for (1) incorporating empathy in ethical AI algorithms, (2) integrating multimodal data formats for ethical AI system design and development, (3) viewing AI ethics as a dynamic, diverse, cumulative, and shared process rather than as a static, self-contained framework to facilitate adaptability without annihilation of values (4) consistent life-long learning to enhance AI accountability

With humans interacting with AI-based systems at an increasing rate, it is necessary to ensure the artificial systems are acting in a manner which reflects understanding of the human. In the case of humans and artificial AI agents operating in the same environment, we note the significance of comprehension and response to the actions or capabilities of a human from an agent's perspective, as well as the possibility to delegate decisions either to humans or to agents, depending on who is deemed more suitable at a certain point in time. Such capabilities will ensure an improved responsiveness and utility of the entire human-AI system. To that end, we investigate the use of cognitively inspired models of behavior to predict the behavior of both human and AI agents. The predicted behavior, and associated performance with respect to a certain goal, is used to delegate control between humans and AI agents through the use of an intermediary entity. As we demonstrate, this allows overcoming potential shortcomings of either humans or agents in the pursuit of a goal.