Research Papers

The Situate AI Guidebook: Co-Designing a Toolkit to Support Multi-Stakeholder Early-stage Deliberations Around Public Sector AI Proposals

Anna Kawakami, Amanda Coston, Haiyi Zhu +2

Public sector agencies are rapidly deploying AI systems to augment or automate critical decisions in real-world contexts like child welfare, criminal justice, and public health. A growing body of work documents how these AI systems often fail to improve services in practice. These failures can often be traced to decisions made during the early stages of AI ideation and design, such as problem formulation. However, today, we lack systematic processes to support effective, early-stage decision-making about whether and under what conditions to move forward with a proposed AI project. To understand how to scaffold such processes in real-world settings, we worked with public sector agency leaders, AI developers, frontline workers, and community advocates across four public sector agencies and three community advocacy groups in the United States. Through an iterative co-design process, we created the Situate AI Guidebook: a structured process centered around a set of deliberation questions to scaffold conversations around (1) goals and intended use or a proposed AI system, (2) societal and legal considerations, (3) data and modeling constraints, and (4) organizational governance factors. We discuss how the guidebook's design is informed by participants' challenges, needs, and desires for improved deliberation processes. We further elaborate on implications for designing responsible AI toolkits in collaboration with public sector agency stakeholders and opportunities for future work to expand upon the guidebook. This design approach can be more broadly adopted to support the co-creation of responsible AI toolkits that scaffold key decision-making processes surrounding the use of AI in the public sector and beyond.

For synergistic interactions between humans and artificial intelligence (AI) systems, AI outputs often need to be explainable to people. Explainable AI (XAI) systems are commonly tested in human user studies. However, whether XAI researchers consider potential cultural differences in human explanatory needs remains unexplored. We highlight psychological research that found significant differences in human explanations between many people from Western, commonly individualist countries and people from non-Western, often collectivist countries. We argue that XAI research currently overlooks these variations and that many popular XAI designs implicitly and problematically assume that Western explanatory needs are shared cross-culturally. Additionally, we systematically reviewed over 200 XAI user studies and found that most studies did not consider relevant cultural variations, sampled only Western populations, but drew conclusions about human-XAI interactions more generally. We also analyzed over 30 literature reviews of XAI studies. Most reviews did not mention cultural differences in explanatory needs or flag overly broad cross-cultural extrapolations of XAI user study results. Combined, our analyses provide evidence of a cultural bias toward Western populations in XAI research, highlighting an important knowledge gap regarding how culturally diverse users may respond to widely used XAI systems that future work can and should address.

With the level of automation increases in vehicles, such as conditional and highly automated vehicles (AVs), drivers are becoming increasingly out of the control loop, especially in unexpected driving scenarios. Although it might be not necessary to require the drivers to intervene on most occasions, it is still important to improve drivers' situation awareness (SA) in unexpected driving scenarios to improve their trust in and acceptance of AVs. In this study, we conceptualized SA at the levels of perception (SA L1), comprehension (SA L2), and projection (SA L3), and proposed an SA level-based explanation framework based on explainable AI. Then, we examined the effects of these explanations and their modalities on drivers' situational trust, cognitive workload, as well as explanation satisfaction. A three (SA levels: SA L1, SA L2 and SA L3) by two (explanation modalities: visual, visual + audio) between-subjects experiment was conducted with 340 participants recruited from Amazon Mechanical Turk. The results indicated that by designing the explanations using the proposed SA-based framework, participants could redirect their attention to the important objects in the traffic and understand their meaning for the AV system. This improved their SA and filled the gap of understanding the correspondence of AV's behavior in the particular situations which also increased their situational trust in AV. The results showed that participants reported the highest trust with SA L2 explanations, although the mental workload was assessed higher in this level. The results also provided insights into the relationship between the amount of information in explanations and modalities, showing that participants were more satisfied with visual-only explanations in the SA L1 and SA L2 conditions and were more satisfied with visual and auditory explanations in the SA L3 condition.

Current models on Explainable Artificial Intelligence (XAI) have shown an evident and quantified lack of reliability for measuring feature-relevance when statistically entangled features are proposed for training deep classifiers. There has been an increase in the application of Deep Learning in clinical trials to predict early diagnosis of neuro-developmental disorders, such as Autism Spectrum Disorder (ASD). However, the inclusion of more reliable saliency-maps to obtain more trustworthy and interpretable metrics using neural activity features is still insufficiently mature for practical applications in diagnostics or clinical trials. Moreover, in ASD research the inclusion of deep classifiers that use neural measures to predict viewed facial emotions is relatively unexplored. Therefore, in this study we propose the evaluation of a Convolutional Neural Network (CNN) for electroencephalography (EEG)-based facial emotion recognition decoding complemented with a novel RemOve-And-Retrain (ROAR) methodology to recover highly relevant features used in the classifier. Specifically, we compare well-known relevance maps such as Layer-Wise Relevance Propagation (LRP), PatternNet, Pattern-Attribution, and Smooth-Grad Squared. This study is the first to consolidate a more transparent feature-relevance calculation for a successful EEG-based facial emotion recognition using a within-subject-trained CNN in typically-developed and ASD individuals.

Rapid development of artificial intelligence (AI) systems amplify many concerns in society. These AI algorithms inherit different biases from humans due to mysterious operational flow and because of that it is becoming adverse in usage. As a result, researchers have started to address the issue by investigating deeper in the direction towards Responsible and Explainable AI. Among variety of applications of AI, facial expression recognition might not be the most important one, yet is considered as a valuable part of human-AI interaction. Evolution of facial expression recognition from the feature based methods to deep learning drastically improve quality of such algorithms. This research work aims to study a gender bias in deep learning methods for facial expression recognition by investigating six distinct neural networks, training them, and further analysed on the presence of bias, according to the three definition of fairness. The main outcomes show which models are gender biased, which are not and how gender of subject affects its emotion recognition. More biased neural networks show bigger accuracy gap in emotion recognition between male and female test sets. Furthermore, this trend keeps for true positive and false positive rates. In addition, due to the nature of the research, we can observe which types of emotions are better classified for men and which for women. Since the topic of biases in facial expression recognition is not well studied, a spectrum of continuation of this research is truly extensive, and may comprise detail analysis of state-of-the-art methods, as well as targeting other biases.

Artificial intelligence (AI) has shown great promise for diagnostic imaging assessments. However, the application of AI to support medical diagnostics in clinical routine comes with many challenges. The algorithms should have high prediction accuracy but also be transparent, understandable and reliable. Thus, explainable artificial intelligence (XAI) is highly relevant for this domain. We present a survey on XAI within digital pathology, a medical imaging sub-discipline with particular characteristics and needs. The review includes several contributions. Firstly, we give a thorough overview of current XAI techniques of potential relevance for deep learning methods in pathology imaging, and categorise them from three different aspects. In doing so, we incorporate uncertainty estimation methods as an integral part of the XAI landscape. We also connect the technical methods to the specific prerequisites in digital pathology and present findings to guide future research efforts. The survey is intended for both technical researchers and medical professionals, one of the objectives being to establish a common ground for cross-disciplinary discussions.

Despite the popularity of explainable AI, there is limited work on effective methods for unsupervised learning. We study algorithms for $k$-means clustering, focusing on a trade-off between explainability and accuracy. Following prior work, we use a small decision tree to partition a dataset into $k$ clusters. This enables us to explain each cluster assignment by a short sequence of single-feature thresholds. While larger trees produce more accurate clusterings, they also require more complex explanations. To allow flexibility, we develop a new explainable $k$-means clustering algorithm, ExKMC, that takes an additional parameter $k' \geq k$ and outputs a decision tree with $k'$ leaves. We use a new surrogate cost to efficiently expand the tree and to label the leaves with one of $k$ clusters. We prove that as $k'$ increases, the surrogate cost is non-increasing, and hence, we trade explainability for accuracy. Empirically, we validate that ExKMC produces a low cost clustering, outperforming both standard decision tree methods and other algorithms for explainable clustering. Implementation of ExKMC available at https://github.com/navefr/ExKMC.

Various recent Artificial Intelligence (AI) system failures, some of which have made the global headlines, have highlighted issues in these systems. These failures have resulted in calls for more ethical AI systems that better take into account their effects on various stakeholders. However, implementing AI ethics into practice is still an on-going challenge. High-level guidelines for doing so exist, devised by governments and private organizations alike, but lack practicality for developers. To address this issue, in this paper, we present a method for implementing AI ethics. The method, ECCOLA, has been iteratively developed using a cyclical action design research approach. The method aims at making the high-level AI ethics principles more practical, making it possible for developers to more easily implement them in practice.

The era of pervasive computing has resulted in countless devices that continuously monitor users and their environment, generating an abundance of user behavioural data. Such data may support improving the quality of service, but may also lead to adverse usages such as surveillance and advertisement. In parallel, Artificial Intelligence (AI) systems are being applied to sensitive fields such as healthcare, justice, or human resources, raising multiple concerns on the trustworthiness of such systems. Trust in AI systems is thus intrinsically linked to ethics, including the ethics of algorithms, the ethics of data, or the ethics of practice. In this paper, we formalise the requirements of trustworthy AI systems through an ethics perspective. We specifically focus on the aspects that can be integrated into the design and development of AI systems. After discussing the state of research and the remaining challenges, we show how a concrete use-case in smart cities can benefit from these methods.

With the advent of GDPR, the domain of explainable AI and model interpretability has gained added impetus. Methods to extract and communicate visibility into decision-making models have become legal requirement. Two specific types of explanations, contrastive and counterfactual have been identified as suitable for human understanding. In this paper, we propose a model agnostic method and its systemic implementation to generate these explanations using shapely additive explanations (SHAP). We discuss a generative pipeline to create contrastive explanations and use it to further to generate counterfactual datapoints. This pipeline is tested and discussed on the IRIS, Wine Quality & Mobile Features dataset. Analysis of the results obtained follows.

Recommender Systems (RS) play an integral role in enhancing user experiences by providing personalized item suggestions. This survey reviews the progress in RS inclusively from 2017 to 2024, effectively connecting theoretical advances with practical applications. We explore the development from traditional RS techniques like content-based and collaborative filtering to advanced methods involving deep learning, graph-based models, reinforcement learning, and large language models. We also discuss specialized systems such as context-aware, review-based, and fairness-aware RS. The primary goal of this survey is to bridge theory with practice. It addresses challenges across various sectors, including e-commerce, healthcare, and finance, emphasizing the need for scalable, real-time, and trustworthy solutions. Through this survey, we promote stronger partnerships between academic research and industry practices. The insights offered by this survey aim to guide industry professionals in optimizing RS deployment and to inspire future research directions, especially in addressing emerging technological and societal trends\footnote. The survey resources are available in the public GitHub repository https://github.com/VectorInstitute/Recommender-Systems-Survey. (Recommender systems, large language models, chatgpt, responsible AI)

D-BIAS: A Causality-Based Human-in-the-Loop System for Tackling Algorithmic Bias

Bhavya Ghai, Klaus Mueller

With the rise of AI, algorithms have become better at learning underlying patterns from the training data including ingrained social biases based on gender, race, etc. Deployment of such algorithms to domains such as hiring, healthcare, law enforcement, etc. has raised serious concerns about fairness, accountability, trust and interpretability in machine learning algorithms. To alleviate this problem, we propose D-BIAS, a visual interactive tool that embodies human-in-the-loop AI approach for auditing and mitigating social biases from tabular datasets. It uses a graphical causal model to represent causal relationships among different features in the dataset and as a medium to inject domain knowledge. A user can detect the presence of bias against a group, say females, or a subgroup, say black females, by identifying unfair causal relationships in the causal network and using an array of fairness metrics. Thereafter, the user can mitigate bias by acting on the unfair causal edges. For each interaction, say weakening/deleting a biased causal edge, the system uses a novel method to simulate a new (debiased) dataset based on the current causal model. Users can visually assess the impact of their interactions on different fairness metrics, utility metrics, data distortion, and the underlying data distribution. Once satisfied, they can download the debiased dataset and use it for any downstream application for fairer predictions. We evaluate D-BIAS by conducting experiments on 3 datasets and also a formal user study. We found that D-BIAS helps reduce bias significantly compared to the baseline debiasing approach across different fairness metrics while incurring little data distortion and a small loss in utility. Moreover, our human-in-the-loop based approach significantly outperforms an automated approach on trust, interpretability and accountability.