Alice Xiang

Aarohi Srivastava, Abhinav Rastogi, Abhishek Rao et al. · allen-ai, amazon-science

Language models demonstrate both quantitative improvement and new qualitative capabilities with increasing scale. Despite their potentially transformative impact, these new capabilities are as yet poorly characterized. In order to inform future research, prepare for disruptive new model capabilities, and ameliorate socially harmful effects, it is vital that we understand the present and near-future capabilities and limitations of language models. To address this challenge, we introduce the Beyond the Imitation Game benchmark (BIG-bench). BIG-bench currently consists of 204 tasks, contributed by 450 authors across 132 institutions. Task topics are diverse, drawing problems from linguistics, childhood development, math, common-sense reasoning, biology, physics, social bias, software development, and beyond. BIG-bench focuses on tasks that are believed to be beyond the capabilities of current language models. We evaluate the behavior of OpenAI's GPT models, Google-internal dense transformer architectures, and Switch-style sparse transformers on BIG-bench, across model sizes spanning millions to hundreds of billions of parameters. In addition, a team of human expert raters performed all tasks in order to provide a strong baseline. Findings include: model performance and calibration both improve with scale, but are poor in absolute terms (and when compared with rater performance); performance is remarkably similar across model classes, though with benefits from sparsity; tasks that improve gradually and predictably commonly involve a large knowledge or memorization component, whereas tasks that exhibit "breakthrough" behavior at a critical scale often involve multiple steps or components, or brittle metrics; social bias typically increases with scale in settings with ambiguous context, but this can be improved with prompting.

Ana Lucic, Sheeraz Ahmad, Amanda Furtado Brinhosa et al. · amazon-science

When using medical images for diagnosis, either by clinicians or artificial intelligence (AI) systems, it is important that the images are of high quality. When an image is of low quality, the medical exam that produced the image often needs to be redone. In telemedicine, a common problem is that the quality issue is only flagged once the patient has left the clinic, meaning they must return in order to have the exam redone. This can be especially difficult for people living in remote regions, who make up a substantial portion of the patients at Portal Telemedicina, a digital healthcare organization based in Brazil. In this paper, we report on ongoing work regarding (i) the development of an AI system for flagging and explaining low-quality medical images in real-time, (ii) an interview study to understand the explanation needs of stakeholders using the AI system at OurCompany, and, (iii) a longitudinal user study design to examine the effect of including explanations on the workflow of the technicians in our clinics. To the best of our knowledge, this would be the first longitudinal study on evaluating the effects of XAI methods on end-users -- stakeholders that use AI systems but do not have AI-specific expertise. We welcome feedback and suggestions on our experimental setup.

Saleh Afroogh, Seyd Ishtiaque Ahmed, Petra Ahrweiler et al. · cmu

This study provides a cross-disciplinary examination of Explainable Artificial Intelligence (XAI) approaches-focusing on deep neural networks (DNNs) and large language models (LLMs)-and identifies empirical and conceptual limitations in current XAI. We discuss critical symptoms that stem from deeper root causes (i.e., two paradoxes, two conceptual confusions, and five false assumptions). These fundamental problems within the current XAI research field reveal three insights: experimentally, XAI exhibits significant flaws; conceptually, it is paradoxical; and pragmatically, further attempts to reform the paradoxical XAI might exacerbate its confusion-demanding fundamental shifts and new research directions. To move beyond XAI's limitations, we propose a four-pronged synthesized paradigm shift toward reliable and certified AI development. These four components include: verification-focused Interactive AI (IAI) to establish scientific community protocols for certifying AI system performance rather than attempting post-hoc explanations, AI Epistemology for rigorous scientific foundations, User-Sensible AI to create context-aware systems tailored to specific user communities, and Model-Centered Interpretability for faithful technical analysis-together offering comprehensive post-XAI research directions.

Jerone T. A. Andrews, Dora Zhao, William Thong et al.

Human-centric computer vision (HCCV) data curation practices often neglect privacy and bias concerns, leading to dataset retractions and unfair models. HCCV datasets constructed through nonconsensual web scraping lack crucial metadata for comprehensive fairness and robustness evaluations. Current remedies are post hoc, lack persuasive justification for adoption, or fail to provide proper contextualization for appropriate application. Our research focuses on proactive, domain-specific recommendations, covering purpose, privacy and consent, and diversity, for curating HCCV evaluation datasets, addressing privacy and bias concerns. We adopt an ante hoc reflective perspective, drawing from current practices, guidelines, dataset withdrawals, and audits, to inform our considerations and recommendations.

Dora Zhao, Jerone T. A. Andrews, Orestis Papakyriakopoulos et al.

Machine learning (ML) datasets, often perceived as neutral, inherently encapsulate abstract and disputed social constructs. Dataset curators frequently employ value-laden terms such as diversity, bias, and quality to characterize datasets. Despite their prevalence, these terms lack clear definitions and validation. Our research explores the implications of this issue by analyzing "diversity" across 135 image and text datasets. Drawing from social sciences, we apply principles from measurement theory to identify considerations and offer recommendations for conceptualizing, operationalizing, and evaluating diversity in datasets. Our findings have broader implications for ML research, advocating for a more nuanced and precise approach to handling value-laden properties in dataset construction.

Mateo Espinosa Zarlenga, Swami Sankaranarayanan, Jerone T. A. Andrews et al.

Deep neural networks trained via empirical risk minimisation often exhibit significant performance disparities across groups, particularly when group and task labels are spuriously correlated (e.g., "grassy background" and "cows"). Existing bias mitigation methods that aim to address this issue often either rely on group labels for training or validation, or require an extensive hyperparameter search. Such data and computational requirements hinder the practical deployment of these methods, especially when datasets are too large to be group-annotated, computational resources are limited, and models are trained through already complex pipelines. In this paper, we propose Targeted Augmentations for Bias Mitigation (TAB), a simple hyperparameter-free framework that leverages the entire training history of a helper model to identify spurious samples, and generate a group-balanced training set from which a robust model can be trained. We show that TAB improves worst-group performance without any group information or model selection, outperforming existing methods while maintaining overall accuracy.

Dora Zhao, Jerone T. A. Andrews, Alice Xiang

As computer vision systems become more widely deployed, there is increasing concern from both the research community and the public that these systems are not only reproducing but amplifying harmful social biases. The phenomenon of bias amplification, which is the focus of this work, refers to models amplifying inherent training set biases at test time. Existing metrics measure bias amplification with respect to single annotated attributes (e.g., $\texttt{computer}$). However, several visual datasets consist of images with multiple attribute annotations. We show models can learn to exploit correlations with respect to multiple attributes (e.g., {$\texttt{computer}$, $\texttt{keyboard}$}), which are not accounted for by current metrics. In addition, we show current metrics can give the erroneous impression that minimal or no bias amplification has occurred as they involve aggregating over positive and negative values. Further, these metrics lack a clear desired value, making them difficult to interpret. To address these shortcomings, we propose a new metric: Multi-Attribute Bias Amplification. We validate our proposed metric through an analysis of gender bias amplification on the COCO and imSitu datasets. Finally, we benchmark bias mitigation methods using our proposed metric, suggesting possible avenues for future bias mitigation

Yusuke Hirota, Jerone T. A. Andrews, Dora Zhao et al.

We tackle societal bias in image-text datasets by removing spurious correlations between protected groups and image attributes. Traditional methods only target labeled attributes, ignoring biases from unlabeled ones. Using text-guided inpainting models, our approach ensures protected group independence from all attributes and mitigates inpainting biases through data filtering. Evaluations on multi-label image classification and image captioning tasks show our method effectively reduces bias without compromising performance across various models.

Keziah Naggita, Julienne LaChance, Alice Xiang

Biases in large-scale image datasets are known to influence the performance of computer vision models as a function of geographic context. To investigate the limitations of standard Internet data collection methods in low- and middle-income countries, we analyze human-centric image geo-diversity on a massive scale using geotagged Flickr images associated with each nation in Africa. We report the quantity and content of available data with comparisons to population-matched nations in Europe as well as the distribution of data according to fine-grained intra-national wealth estimates. Temporal analyses are performed at two-year intervals to expose emerging data trends. Furthermore, we present findings for an ``othering'' phenomenon as evidenced by a substantial number of images from Africa being taken by non-local photographers. The results of our study suggest that further work is required to capture image data representative of African people and their environments and, ultimately, to improve the applicability of computer vision models in a global context.

Jerone T. A. Andrews, Przemyslaw Joniak, Alice Xiang

Few datasets contain self-identified sensitive attributes, inferring attributes risks introducing additional biases, and collecting attributes can carry legal risks. Besides, categorical labels can fail to reflect the continuous nature of human phenotypic diversity, making it difficult to compare the similarity between same-labeled faces. To address these issues, we present A View From Somewhere (AVFS) -- a dataset of 638,180 human judgments of face similarity. We demonstrate the utility of AVFS for learning a continuous, low-dimensional embedding space aligned with human perception. Our embedding space, induced under a novel conditional framework, not only enables the accurate prediction of face similarity, but also provides a human-interpretable decomposition of the dimensions used in the human-decision making process, and the importance distinct annotators place on each dimension. We additionally show the practicality of the dimensions for collecting continuous attributes, performing classification, and comparing dataset attribute disparities.

Stanley Bryan Z. Hua, Mandy Rickard, John Weaver et al.

Previous work has shown the potential of deep learning to predict renal obstruction using kidney ultrasound images. However, these image-based classifiers have been trained with the goal of single-visit inference in mind. We compare methods from video action recognition (i.e. convolutional pooling, LSTM, TSM) to adapt single-visit convolutional models to handle multiple visit inference. We demonstrate that incorporating images from a patient's past hospital visits provides only a small benefit for the prediction of obstructive hydronephrosis. Therefore, inclusion of prior ultrasounds is beneficial, but prediction based on the latest ultrasound is sufficient for patient risk stratification.

Rui-Jie Yew, Alice Xiang

Harms resulting from the development and deployment of facial processing technologies (FPT) have been met with increasing controversy. Several states and cities in the U.S. have banned the use of facial recognition by law enforcement and governments, but FPT are still being developed and used in a wide variety of contexts where they primarily are regulated by state biometric information privacy laws. Among these laws, the 2008 Illinois Biometric Information Privacy Act (BIPA) has generated a significant amount of litigation. Yet, with most BIPA lawsuits reaching settlements before there have been meaningful clarifications of relevant technical intricacies and legal definitions, there remains a great degree of uncertainty as to how exactly this law applies to FPT. What we have found through applications of BIPA in FPT litigation so far, however, points to potential disconnects between technical and legal communities. This paper analyzes what we know based on BIPA court proceedings and highlights these points of tension: areas where the technical operationalization of BIPA may create unintended and undesirable incentives for FPT development, as well as areas where BIPA litigation can bring to light the limitations of solely technical methods in achieving legal privacy values. These factors are relevant for (i) reasoning about biometric information privacy laws as a governing mechanism for FPT, (ii) assessing the potential harms of FPT, and (iii) providing incentives for the mitigation of these harms. By illuminating these considerations, we hope to empower courts and lawmakers to take a more nuanced approach to regulating FPT and developers to better understand privacy values in the current U.S. legal landscape.

William Thong, Przemyslaw Joniak, Alice Xiang

This paper strives to measure apparent skin color in computer vision, beyond a unidimensional scale on skin tone. In their seminal paper Gender Shades, Buolamwini and Gebru have shown how gender classification systems can be biased against women with darker skin tones. Subsequently, fairness researchers and practitioners have adopted the Fitzpatrick skin type classification as a common measure to assess skin color bias in computer vision systems. While effective, the Fitzpatrick scale only focuses on the skin tone ranging from light to dark. Towards a more comprehensive measure of skin color, we introduce the hue angle ranging from red to yellow. When applied to images, the hue dimension reveals additional biases related to skin color in both computer vision datasets and models. We then recommend multidimensional skin color scales, relying on both skin tone and hue, for fairness assessments.

Wiebke Hutiri, Morgan Scheuerman, Shruti Nagpal et al.

This paper argues that a one-size-fits-all approach to specifying consent for the use of creative works in generative AI is insufficient. Real-world ownership and rights holder structures, the imitation of artistic styles and likeness, and the limitless contexts of use of AI outputs make the status quo of binary consent with opt-in by default untenable. To move beyond the current impasse, we consider levers of control in generative AI workflows at training, inference, and dissemination. Based on these insights, we position inference-time opt-in as an overlooked opportunity for nuanced consent verification. We conceptualize nuanced consent conditions for opt-in and propose an agent-based inference-time opt-in architecture to verify if user intent requests meet conditional consent granted by rights holders. In a case study for music, we demonstrate that nuanced opt-in at inference can account for established rights and re-establish a balance of power between rights holders and AI developers.

Fabio Morreale, Wiebke Hutiri, Joan Serrà et al.

The rise of AI-generated music is diluting royalty pools and revealing structural flaws in existing remuneration frameworks, challenging the well-established artist compensation systems in the music industry. Existing compensation solutions, such as piecemeal licensing agreements, lack scalability and technical rigour, while current data attribution mechanisms provide only uncertain estimates and are rarely implemented in practice. This paper introduces a framework for a generative music infrastructure centred on direct attribution, transparent royalty distribution, and granular control for artists and rights' holders. We distinguish ontologically between the training set and the inference set, which allows us to propose two complementary forms of attribution: training-time attribution and inference-time attribution. We here favour inference-time attribution, as it enables direct, verifiable compensation whenever an artist's catalogue is used to condition a generated output. Besides, users benefit from the ability to condition generations on specific songs and receive transparent information about attribution and permitted usage. Our approach offers an ethical and practical solution to the pressing need for robust compensation mechanisms in the era of AI-generated music, ensuring that provenance and fairness are embedded at the core of generative systems.

Wiebke Hutiri, Mircea Cimpoi, Morgan Scheuerman et al.

Dataset transparency is a key enabler of responsible AI, but insights into multimodal dataset attributes that impact trustworthy and ethical aspects of AI applications remain scarce and are difficult to compare across datasets. To address this challenge, we introduce Trustworthy and Ethical Dataset Indicators (TEDI) that facilitate the systematic, empirical analysis of dataset documentation. TEDI encompasses 143 fine-grained indicators that characterize trustworthy and ethical attributes of multimodal datasets and their collection processes. The indicators are framed to extract verifiable information from dataset documentation. Using TEDI, we manually annotated and analyzed over 100 multimodal datasets that include human voices. We further annotated data sourcing, size, and modality details to gain insights into the factors that shape trustworthy and ethical dimensions across datasets. We find that only a select few datasets have documented attributes and practices pertaining to consent, privacy, and harmful content indicators. The extent to which these and other ethical indicators are addressed varies based on the data collection method, with documentation of datasets collected via crowdsourced and direct collection approaches being more likely to mention them. Scraping dominates scale at the cost of ethical indicators, but is not the only viable collection method. Our approach and empirical insights contribute to increasing dataset transparency along trustworthy and ethical dimensions and pave the way for automating the tedious task of extracting information from dataset documentation in future.

Dora Zhao, Morgan Klaus Scheuerman, Pooja Chitre et al.

Despite extensive efforts to create fairer machine learning (ML) datasets, there remains a limited understanding of the practical aspects of dataset curation. Drawing from interviews with 30 ML dataset curators, we present a comprehensive taxonomy of the challenges and trade-offs encountered throughout the dataset curation lifecycle. Our findings underscore overarching issues within the broader fairness landscape that impact data curation. We conclude with recommendations aimed at fostering systemic changes to better facilitate fair dataset curation practices.

Wiebke Hutiri, Oresiti Papakyriakopoulos, Alice Xiang

The rapid and wide-scale adoption of AI to generate human speech poses a range of significant ethical and safety risks to society that need to be addressed. For example, a growing number of speech generation incidents are associated with swatting attacks in the United States, where anonymous perpetrators create synthetic voices that call police officers to close down schools and hospitals, or to violently gain access to innocent citizens' homes. Incidents like this demonstrate that multimodal generative AI risks and harms do not exist in isolation, but arise from the interactions of multiple stakeholders and technical AI systems. In this paper we analyse speech generation incidents to study how patterns of specific harms arise. We find that specific harms can be categorised according to the exposure of affected individuals, that is to say whether they are a subject of, interact with, suffer due to, or are excluded from speech generation systems. Similarly, specific harms are also a consequence of the motives of the creators and deployers of the systems. Based on these insights we propose a conceptual framework for modelling pathways to ethical and safety harms of AI, which we use to develop a taxonomy of harms of speech generators. Our relational approach captures the complexity of risks and harms in sociotechnical AI systems, and yields a taxonomy that can support appropriate policy interventions and decision making for the responsible development and release of speech generation models.

Orestis Papakyriakopoulos, Alice Xiang

Speech AI Technologies are largely trained on publicly available datasets or by the massive web-crawling of speech. In both cases, data acquisition focuses on minimizing collection effort, without necessarily taking the data subjects' protection or user needs into consideration. This results to models that are not robust when used on users who deviate from the dominant demographics in the training set, discriminating individuals having different dialects, accents, speaking styles, and disfluencies. In this talk, we use automatic speech recognition as a case study and examine the properties that ethical speech datasets should possess towards responsible AI applications. We showcase diversity issues, inclusion practices, and necessary considerations that can improve trained models, while facilitating model explainability and protecting users and data subjects. We argue for the legal & privacy protection of data subjects, targeted data sampling corresponding to user demographics & needs, appropriate meta data that ensure explainability & accountability in cases of model failure, and the sociotechnical \& situated model design. We hope this talk can inspire researchers \& practitioners to design and use more human-centric datasets in speech technologies and other domains, in ways that empower and respect users, while improving machine learning models' robustness and utility.

Aida Rahmattalabi, Alice Xiang

In recent years, there has been increasing interest in causal reasoning for designing fair decision-making systems due to its compatibility with legal frameworks, interpretability for human stakeholders, and robustness to spurious correlations inherent in observational data, among other factors. The recent attention to causal fairness, however, has been accompanied with great skepticism due to practical and epistemological challenges with applying current causal fairness approaches in the literature. Motivated by the long-standing empirical work on causality in econometrics, social sciences, and biomedical sciences, in this paper we lay out the conditions for appropriate application of causal fairness under the "potential outcomes framework." We highlight key aspects of causal inference that are often ignored in the causal fairness literature. In particular, we discuss the importance of specifying the nature and timing of interventions on social categories such as race or gender. Precisely, instead of postulating an intervention on immutable attributes, we propose a shift in focus to their perceptions and discuss the implications for fairness evaluation. We argue that such conceptualization of the intervention is key in evaluating the validity of causal assumptions and conducting sound causal analysis including avoiding post-treatment bias. Subsequently, we illustrate how causality can address the limitations of existing fairness metrics, including those that depend upon statistical correlations. Specifically, we introduce causal variants of common statistical notions of fairness, and we make a novel observation that under the causal framework there is no fundamental disagreement between different notions of fairness. Finally, we conduct extensive experiments where we demonstrate our approach for evaluating and mitigating unfairness, specially when post-treatment variables are present.

Ana Lucic, Madhulika Srikumar, Umang Bhatt et al.

Given that there are a variety of stakeholders involved in, and affected by, decisions from machine learning (ML) models, it is important to consider that different stakeholders have different transparency needs. Previous work found that the majority of deployed transparency mechanisms primarily serve technical stakeholders. In our work, we want to investigate how well transparency mechanisms might work in practice for a more diverse set of stakeholders by conducting a large-scale, mixed-methods user study across a range of organizations, within a particular industry such as health care, criminal justice, or content moderation. In this paper, we outline the setup for our study.

Daniel E. Ho, Alice Xiang

While there has been a flurry of research in algorithmic fairness, what is less recognized is that modern antidiscrimination law may prohibit the adoption of such techniques. We make three contributions. First, we discuss how such approaches will likely be deemed "algorithmic affirmative action," posing serious legal risks of violating equal protection, particularly under the higher education jurisprudence. Such cases have increasingly turned toward anticlassification, demanding "individualized consideration" and barring formal, quantitative weights for race regardless of purpose. This case law is hence fundamentally incompatible with fairness in machine learning. Second, we argue that the government-contracting cases offer an alternative grounding for algorithmic fairness, as these cases permit explicit and quantitative race-based remedies based on historical discrimination by the actor. Third, while limited, this doctrinal approach also guides the future of algorithmic fairness, mandating that adjustments be calibrated to the entity's responsibility for historical discrimination causing present-day disparities. The contractor cases provide a legally viable path for algorithmic fairness under current constitutional doctrine but call for more research at the intersection of algorithmic fairness and causal inference to ensure that bias mitigation is tailored to specific causes and mechanisms of bias.

Umang Bhatt, Javier Antorán, Yunfeng Zhang et al.

Algorithmic transparency entails exposing system properties to various stakeholders for purposes that include understanding, improving, and contesting predictions. Until now, most research into algorithmic transparency has predominantly focused on explainability. Explainability attempts to provide reasons for a machine learning model's behavior to stakeholders. However, understanding a model's specific behavior alone might not be enough for stakeholders to gauge whether the model is wrong or lacks sufficient knowledge to solve the task at hand. In this paper, we argue for considering a complementary form of transparency by estimating and communicating the uncertainty associated with model predictions. First, we discuss methods for assessing uncertainty. Then, we characterize how uncertainty can be used to mitigate model unfairness, augment decision-making, and build trustworthy systems. Finally, we outline methods for displaying uncertainty to stakeholders and recommend how to collect information required for incorporating uncertainty into existing ML pipelines. This work constitutes an interdisciplinary review drawn from literature spanning machine learning, visualization/HCI, design, decision-making, and fairness. We aim to encourage researchers and practitioners to measure, communicate, and use uncertainty as a form of transparency.

McKane Andrus, Elena Spitzer, Jeffrey Brown et al.

As calls for fair and unbiased algorithmic systems increase, so too does the number of individuals working on algorithmic fairness in industry. However, these practitioners often do not have access to the demographic data they feel they need to detect bias in practice. Even with the growing variety of toolkits and strategies for working towards algorithmic fairness, they almost invariably require access to demographic attributes or proxies. We investigated this dilemma through semi-structured interviews with 38 practitioners and professionals either working in or adjacent to algorithmic fairness. Participants painted a complex picture of what demographic data availability and use look like on the ground, ranging from not having access to personal data of any kind to being legally required to collect and use demographic data for discrimination assessments. In many domains, demographic data collection raises a host of difficult questions, including how to balance privacy and fairness, how to define relevant social categories, how to ensure meaningful consent, and whether it is appropriate for private companies to infer someone's demographics. Our research suggests challenges that must be considered by businesses, regulators, researchers, and community groups in order to enable practitioners to address algorithmic bias in practice. Critically, we do not propose that the overall goal of future work should be to simply lower the barriers to collecting demographic data. Rather, our study surfaces a swath of normative questions about how, when, and whether this data should be procured, and, in cases where it is not, what should still be done to mitigate bias.

Umang Bhatt, McKane Andrus, Adrian Weller et al.

As machine learning is increasingly deployed in high-stakes contexts affecting people's livelihoods, there have been growing calls to open the black box and to make machine learning algorithms more explainable. Providing useful explanations requires careful consideration of the needs of stakeholders, including end-users, regulators, and domain experts. Despite this need, little work has been done to facilitate inter-stakeholder conversation around explainable machine learning. To help address this gap, we conducted a closed-door, day-long workshop between academics, industry experts, legal scholars, and policymakers to develop a shared language around explainability and to understand the current shortcomings of and potential solutions for deploying explainable machine learning in service of transparency goals. We also asked participants to share case studies in deploying explainable machine learning at scale. In this paper, we provide a short summary of various case studies of explainable machine learning, lessons from those studies, and discuss open challenges.

Alice Xiang, Inioluwa Deborah Raji

Past literature has been effective in demonstrating ideological gaps in machine learning (ML) fairness definitions when considering their use in complex socio-technical systems. However, we go further to demonstrate that these definitions often misunderstand the legal concepts from which they purport to be inspired, and consequently inappropriately co-opt legal language. In this paper, we demonstrate examples of this misalignment and discuss the differences in ML terminology and their legal counterparts, as well as what both the legal and ML fairness communities can learn from these tensions. We focus this paper on U.S. anti-discrimination law since the ML fairness research community regularly references terms from this body of law.

Umang Bhatt, Alice Xiang, Shubham Sharma et al.

Explainable machine learning offers the potential to provide stakeholders with insights into model behavior by using various methods such as feature importance scores, counterfactual explanations, or influential training data. Yet there is little understanding of how organizations use these methods in practice. This study explores how organizations view and use explainability for stakeholder consumption. We find that, currently, the majority of deployments are not for end users affected by the model but rather for machine learning engineers, who use explainability to debug the model itself. There is thus a gap between explainability in practice and the goal of transparency, since explanations primarily serve internal stakeholders rather than external ones. Our study synthesizes the limitations of current explainability techniques that hamper their use for end users. To facilitate end user interaction, we develop a framework for establishing clear goals for explainability. We end by discussing concerns raised regarding explainability.