Research Papers

Being able to explain the prediction to clinical end-users is a necessity to leverage the power of artificial intelligence (AI) models for clinical decision support. For medical images, a feature attribution map, or heatmap, is the most common form of explanation that highlights important features for AI models' prediction. However, it is unknown how well heatmaps perform on explaining decisions on multi-modal medical images, where each image modality or channel visualizes distinct clinical information of the same underlying biomedical phenomenon. Understanding such modality-dependent features is essential for clinical users' interpretation of AI decisions. To tackle this clinically important but technically ignored problem, we propose the modality-specific feature importance (MSFI) metric. It encodes clinical image and explanation interpretation patterns of modality prioritization and modality-specific feature localization. We conduct a clinical requirement-grounded, systematic evaluation using computational methods and a clinician user study. Results show that the examined 16 heatmap algorithms failed to fulfill clinical requirements to correctly indicate AI model decision process or decision quality. The evaluation and MSFI metric can guide the design and selection of XAI algorithms to meet clinical requirements on multi-modal explanation.

In July 2023, New York City (NYC) initiated the first algorithm auditing system for commercial machine-learning systems. Local Law 144 (LL 144) mandates NYC-based employers using automated employment decision-making tools (AEDTs) in hiring to undergo annual bias audits conducted by an independent auditor. This paper examines lessons from LL 144 for other national algorithm auditing attempts. Through qualitative interviews with 16 experts and practitioners within the regime, we find that LL 144 has not effectively established an auditing regime. The law fails to clearly define key aspects, such as AEDTs and independent auditors, leading auditors, AEDT vendors, and companies using AEDTs to define the law's practical implementation in ways that failed to protect job applicants. Contributing factors include the law's flawed transparency-driven theory of change, industry lobbying narrowing the definition of AEDTs, practical and cultural challenges faced by auditors in accessing data, and wide disagreement over what constitutes a legitimate auditor, resulting in four distinct 'auditor roles.' We conclude with four recommendations for policymakers seeking to create similar bias auditing regimes, emphasizing clearer definitions, metrics, and increased accountability. By exploring LL 144 through the lens of auditors, our paper advances the evidence base around audit as an accountability mechanism, providing guidance for policymakers seeking to create similar regimes.

Explaining Deep Classification of Time-Series Data with Learned Prototypes

Alan H. Gee, Diego Garcia-Olano, Joydeep Ghosh +1

The emergence of deep learning networks raises a need for explainable AI so that users and domain experts can be confident applying them to high-risk decisions. In this paper, we leverage data from the latent space induced by deep learning models to learn stereotypical representations or "prototypes" during training to elucidate the algorithmic decision-making process. We study how leveraging prototypes effect classification decisions of two dimensional time-series data in a few different settings: (1) electrocardiogram (ECG) waveforms to detect clinical bradycardia, a slowing of heart rate, in preterm infants, (2) respiration waveforms to detect apnea of prematurity, and (3) audio waveforms to classify spoken digits. We improve upon existing models by optimizing for increased prototype diversity and robustness, visualize how these prototypes in the latent space are used by the model to distinguish classes, and show that prototypes are capable of learning features on two dimensional time-series data to produce explainable insights during classification tasks. We show that the prototypes are capable of learning real-world features - bradycardia in ECG, apnea in respiration, and articulation in speech - as well as features within sub-classes. Our novel work leverages learned prototypical framework on two dimensional time-series data to produce explainable insights during classification tasks.

Gradient Boost Decision Trees (GBDT) is a powerful additive model based on tree ensembles. Its nature makes GBDT a black-box model even though there are multiple explainable artificial intelligence (XAI) models obtaining information by reinterpreting the model globally and locally. Each tree of the ensemble is a transparent model itself but the final outcome is the result of a sum of these trees and it is not easy to clarify. In this paper, a feature contribution method for GBDT is developed. The proposed method takes advantage of the GBDT architecture to calculate the contribution of each feature using the residue of each node. This algorithm allows to calculate the sequence of node decisions given a prediction. Theoretical proofs and multiple experiments have been carried out to demonstrate the performance of our method which is not only a local explicability model for the GBDT algorithm but also a unique option that reflects GBDTs internal behavior. The proposal is aligned to the contribution of characteristics having impact in some artificial intelligence problems such as ethical analysis of Artificial Intelligence (AI) and comply with the new European laws such as the General Data Protection Regulation (GDPR) about the right to explain and nondiscrimination.

Public attention towards explainability of artificial intelligence (AI) systems has been rising in recent years to offer methodologies for human oversight. This has translated into the proliferation of research outputs, such as from Explainable AI, to enhance transparency and control for system debugging and monitoring, and intelligibility of system process and output for user services. Yet, such outputs are difficult to adopt on a practical level due to a lack of a common regulatory baseline, and the contextual nature of explanations. Governmental policies are now attempting to tackle such exigence, however it remains unclear to what extent published communications, regulations, and standards adopt an informed perspective to support research, industry, and civil interests. In this study, we perform the first thematic and gap analysis of this plethora of policies and standards on explainability in the EU, US, and UK. Through a rigorous survey of policy documents, we first contribute an overview of governmental regulatory trajectories within AI explainability and its sociotechnical impacts. We find that policies are often informed by coarse notions and requirements for explanations. This might be due to the willingness to conciliate explanations foremost as a risk management tool for AI oversight, but also due to the lack of a consensus on what constitutes a valid algorithmic explanation, and how feasible the implementation and deployment of such explanations are across stakeholders of an organization. Informed by AI explainability research, we conduct a gap analysis of existing policies, leading us to formulate a set of recommendations on how to address explainability in regulations for AI systems, especially discussing the definition, feasibility, and usability of explanations, as well as allocating accountability to explanation providers.

A Human-Grounded Evaluation of SHAP for Alert Processing

Hilde J. P. Weerts, Werner van Ipenburg, Mykola Pechenizkiy

In the past years, many new explanation methods have been proposed to achieve interpretability of machine learning predictions. However, the utility of these methods in practical applications has not been researched extensively. In this paper we present the results of a human-grounded evaluation of SHAP, an explanation method that has been well-received in the XAI and related communities. In particular, we study whether this local model-agnostic explanation method can be useful for real human domain experts to assess the correctness of positive predictions, i.e. alerts generated by a classifier. We performed experimentation with three different groups of participants (159 in total), who had basic knowledge of explainable machine learning. We performed a qualitative analysis of recorded reflections of experiment participants performing alert processing with and without SHAP information. The results suggest that the SHAP explanations do impact the decision-making process, although the model's confidence score remains to be a leading source of evidence. We statistically test whether there is a significant difference in task utility metrics between tasks for which an explanation was available and tasks in which it was not provided. As opposed to common intuitions, we did not find a significant difference in alert processing performance when a SHAP explanation is available compared to when it is not.

Artificial Intelligence (AI) solutions and technologies are being increasingly adopted in smart systems context, however, such technologies are continuously concerned with ethical uncertainties. Various guidelines, principles, and regulatory frameworks are designed to ensure that AI technologies bring ethical well-being. However, the implications of AI ethics principles and guidelines are still being debated. To further explore the significance of AI ethics principles and relevant challenges, we conducted a survey of 99 representative AI practitioners and lawmakers (e.g., AI engineers, lawyers) from twenty countries across five continents. To the best of our knowledge, this is the first empirical study that encapsulates the perceptions of two different types of population (AI practitioners and lawmakers) and the study findings confirm that transparency, accountability, and privacy are the most critical AI ethics principles. On the other hand, lack of ethical knowledge, no legal frameworks, and lacking monitoring bodies are found the most common AI ethics challenges. The impact analysis of the challenges across AI ethics principles reveals that conflict in practice is a highly severe challenge. Moreover, the perceptions of practitioners and lawmakers are statistically correlated with significant differences for particular principles (e.g. fairness, freedom) and challenges (e.g. lacking monitoring bodies, machine distortion). Our findings stimulate further research, especially empowering existing capability maturity models to support the development and quality assessment of ethics-aware AI systems.

In this paper, we investigate the computational intelligibility of Boolean classifiers, characterized by their ability to answer XAI queries in polynomial time. The classifiers under consideration are decision trees, DNF formulae, decision lists, decision rules, tree ensembles, and Boolean neural nets. Using 9 XAI queries, including both explanation queries and verification queries, we show the existence of large intelligibility gap between the families of classifiers. On the one hand, all the 9 XAI queries are tractable for decision trees. On the other hand, none of them is tractable for DNF formulae, decision lists, random forests, boosted decision trees, Boolean multilayer perceptrons, and binarized neural networks.

AI Governance in Higher Education: Case Studies of Guidance at Big Ten Universities

Chuhao Wu, He Zhang, John M. Carroll

Generative AI has drawn significant attention from stakeholders in higher education. As it introduces new opportunities for personalized learning and tutoring support, it simultaneously poses challenges to academic integrity and leads to ethical issues. Consequently, governing responsible AI usage within higher education institutions (HEIs) becomes increasingly important. Leading universities have already published guidelines on Generative AI, with most attempting to embrace this technology responsibly. This study provides a new perspective by focusing on strategies for responsible AI governance as demonstrated in these guidelines. Through a case study of 14 prestigious universities in the United States, we identified the multi-unit governance of AI, the role-specific governance of AI, and the academic characteristics of AI governance from their AI guidelines. The strengths and potential limitations of these strategies and characteristics are discussed. The findings offer practical implications for guiding responsible AI usage in HEIs and beyond.

Advances in Generative Artificial Intelligence (AI) are resulting in AI-generated media output that is (nearly) indistinguishable from human-created content. This can drastically impact users and the media sector, especially given global risks of misinformation. While the currently discussed European AI Act aims at addressing these risks through Article 52's AI transparency obligations, its interpretation and implications remain unclear. In this early work, we adopt a participatory AI approach to derive key questions based on Article 52's disclosure obligations. We ran two workshops with researchers, designers, and engineers across disciplines (N=16), where participants deconstructed Article 52's relevant clauses using the 5W1H framework. We contribute a set of 149 questions clustered into five themes and 18 sub-themes. We believe these can not only help inform future legal developments and interpretations of Article 52, but also provide a starting point for Human-Computer Interaction research to (re-)examine disclosure transparency from a human-centered AI lens.

A Transparency Index Framework for AI in Education

Muhammad Ali Chaudhry, Mutlu Cukurova, Rose Luckin

Numerous AI ethics checklists and frameworks have been proposed focusing on different dimensions of ethical AI such as fairness, explainability, and safety. Yet, no such work has been done on developing transparent AI systems for real-world educational scenarios. This paper presents a Transparency Index framework that has been iteratively co-designed with different stakeholders of AI in education, including educators, ed-tech experts, and AI practitioners. We map the requirements of transparency for different categories of stakeholders of AI in education and demonstrate that transparency considerations are embedded in the entire AI development process from the data collection stage until the AI system is deployed in the real world and iteratively improved. We also demonstrate how transparency enables the implementation of other ethical AI dimensions in Education like interpretability, accountability, and safety. In conclusion, we discuss the directions for future research in this newly emerging field. The main contribution of this study is that it highlights the importance of transparency in developing AI-powered educational technologies and proposes an index framework for its conceptualization for AI in education.

A pervasive design issue of AI systems is their explainability--how to provide appropriate information to help users understand the AI. The technical field of explainable AI (XAI) has produced a rich toolbox of techniques. Designers are now tasked with the challenges of how to select the most suitable XAI techniques and translate them into UX solutions. Informed by our previous work studying design challenges around XAI UX, this work proposes a design process to tackle these challenges. We review our and related prior work to identify requirements that the process should fulfill, and accordingly, propose a Question-Driven Design Process that grounds the user needs, choices of XAI techniques, design, and evaluation of XAI UX all in the user questions. We provide a mapping guide between prototypical user questions and exemplars of XAI techniques to reframe the technical space of XAI, also serving as boundary objects to support collaboration between designers and AI engineers. We demonstrate it with a use case of designing XAI for healthcare adverse events prediction, and discuss lessons learned for tackling design challenges of AI systems.