Simone Stumpf

Luca Longo, Mario Brcic, Federico Cabitza et al.

As systems based on opaque Artificial Intelligence (AI) continue to flourish in diverse real-world applications, understanding these black box models has become paramount. In response, Explainable AI (XAI) has emerged as a field of research with practical and ethical benefits across various domains. This paper not only highlights the advancements in XAI and its application in real-world scenarios but also addresses the ongoing challenges within XAI, emphasizing the need for broader perspectives and collaborative efforts. We bring together experts from diverse fields to identify open problems, striving to synchronize research agendas and accelerate XAI in practical applications. By fostering collaborative discussion and interdisciplinary cooperation, we aim to propel XAI forward, contributing to its continued success. Our goal is to put forward a comprehensive proposal for advancing XAI. To achieve this goal, we present a manifesto of 27 open problems categorized into nine categories. These challenges encapsulate the complexities and nuances of XAI and offer a road map for future research. For each problem, we provide promising research directions in the hope of harnessing the collective intelligence of interested stakeholders.

Mohammad Tahaei, Marios Constantinides, Daniele Quercia et al.

In recent years, the CHI community has seen significant growth in research on Human-Centered Responsible Artificial Intelligence. While different research communities may use different terminology to discuss similar topics, all of this work is ultimately aimed at developing AI that benefits humanity while being grounded in human rights and ethics, and reducing the potential harms of AI. In this special interest group, we aim to bring together researchers from academia and industry interested in these topics to map current and future research trends to advance this important area of research by fostering collaboration and sharing ideas.

Aditya Bhattacharya, Simone Stumpf, Lucija Gosak et al.

In the realm of interactive machine-learning systems, the provision of explanations serves as a vital aid in the processes of debugging and enhancing prediction models. However, the extent to which various global model-centric and data-centric explanations can effectively assist domain experts in detecting and resolving potential data-related issues for the purpose of model improvement has remained largely unexplored. In this technical report, we summarise the key findings of our two user studies. Our research involved a comprehensive examination of the impact of global explanations rooted in both data-centric and model-centric perspectives within systems designed to support healthcare experts in optimising machine learning models through both automated and manual data configurations. To empirically investigate these dynamics, we conducted two user studies, comprising quantitative analysis involving a sample size of 70 healthcare experts and qualitative assessments involving 30 healthcare experts. These studies were aimed at illuminating the influence of different explanation types on three key dimensions: trust, understandability, and model improvement. Results show that global model-centric explanations alone are insufficient for effectively guiding users during the intricate process of data configuration. In contrast, data-centric explanations exhibited their potential by enhancing the understanding of system changes that occur post-configuration. However, a combination of both showed the highest level of efficacy for fostering trust, improving understandability, and facilitating model enhancement among healthcare experts. We also present essential implications for developing interactive machine-learning systems driven by explanations. These insights can guide the creation of more effective systems that empower domain experts to harness the full potential of machine learning

Yuri Nakao, Lorenzo Strappelli, Simone Stumpf et al.

With Artificial intelligence (AI) to aid or automate decision-making advancing rapidly, a particular concern is its fairness. In order to create reliable, safe and trustworthy systems through human-centred artificial intelligence (HCAI) design, recent efforts have produced user interfaces (UIs) for AI experts to investigate the fairness of AI models. In this work, we provide a design space exploration that supports not only data scientists but also domain experts to investigate AI fairness. Using loan applications as an example, we held a series of workshops with loan officers and data scientists to elicit their requirements. We instantiated these requirements into FairHIL, a UI to support human-in-the-loop fairness investigations, and describe how this UI could be generalized to other use cases. We evaluated FairHIL through a think-aloud user study. Our work contributes better designs to investigate an AI model's fairness-and move closer towards responsible AI.

Yuri Nakao, Simone Stumpf, Subeida Ahmed et al.

Ensuring fairness in artificial intelligence (AI) is important to counteract bias and discrimination in far-reaching applications. Recent work has started to investigate how humans judge fairness and how to support machine learning (ML) experts in making their AI models fairer. Drawing inspiration from an Explainable AI (XAI) approach called \emph{explanatory debugging} used in interactive machine learning, our work explores designing interpretable and interactive human-in-the-loop interfaces that allow ordinary end-users without any technical or domain background to identify potential fairness issues and possibly fix them in the context of loan decisions. Through workshops with end-users, we co-designed and implemented a prototype system that allowed end-users to see why predictions were made, and then to change weights on features to "debug" fairness issues. We evaluated the use of this prototype system through an online study. To investigate the implications of diverse human values about fairness around the globe, we also explored how cultural dimensions might play a role in using this prototype. Our results contribute to the design of interfaces to allow end-users to be involved in judging and addressing AI fairness through a human-in-the-loop approach.

Lin Luo, Yuri Nakao, Mathieu Chollet et al.

Numerous fairness metrics have been proposed and employed by artificial intelligence (AI) experts to quantitatively measure bias and define fairness in AI models. Recognizing the need to accommodate stakeholders' diverse fairness understandings, efforts are underway to solicit their input. However, conveying AI fairness metrics to stakeholders without AI expertise, capturing their personal preferences, and seeking a collective consensus remain challenging and underexplored. To bridge this gap, we propose a new framework, EARN Fairness, which facilitates collective metric decisions among stakeholders without requiring AI expertise. The framework features an adaptable interactive system and a stakeholder-centered EARN Fairness process to Explain fairness metrics, Ask stakeholders' personal metric preferences, Review metrics collectively, and Negotiate a consensus on metric selection. To gather empirical results, we applied the framework to a credit rating scenario and conducted a user study involving 18 decision subjects without AI knowledge. We identify their personal metric preferences and their acceptable level of unfairness in individual sessions. Subsequently, we uncovered how they reached metric consensus in team sessions. Our work shows that the EARN Fairness framework enables stakeholders to express personal preferences and reach consensus, providing practical guidance for implementing human-centered AI fairness in high-risk contexts. Through this approach, we aim to harmonize fairness expectations of diverse stakeholders, fostering more equitable and inclusive AI fairness.

Daniela Massiceti, Luisa Zintgraf, John Bronskill et al.

Object recognition has made great advances in the last decade, but predominately still relies on many high-quality training examples per object category. In contrast, learning new objects from only a few examples could enable many impactful applications from robotics to user personalization. Most few-shot learning research, however, has been driven by benchmark datasets that lack the high variation that these applications will face when deployed in the real-world. To close this gap, we present the ORBIT dataset and benchmark, grounded in the real-world application of teachable object recognizers for people who are blind/low-vision. The dataset contains 3,822 videos of 486 objects recorded by people who are blind/low-vision on their mobile phones. The benchmark reflects a realistic, highly challenging recognition problem, providing a rich playground to drive research in robustness to few-shot, high-variation conditions. We set the benchmark's first state-of-the-art and show there is massive scope for further innovation, holding the potential to impact a broad range of real-world vision applications including tools for the blind/low-vision community. We release the dataset at https://doi.org/10.25383/city.14294597 and benchmark code at https://github.com/microsoft/ORBIT-Dataset.

Aditya Bhattacharya, Simone Stumpf, Lucija Gosak et al.

Explanations in interactive machine-learning systems facilitate debugging and improving prediction models. However, the effectiveness of various global model-centric and data-centric explanations in aiding domain experts to detect and resolve potential data issues for model improvement remains unexplored. This research investigates the influence of data-centric and model-centric global explanations in systems that support healthcare experts in optimising models through automated and manual data configurations. We conducted quantitative (n=70) and qualitative (n=30) studies with healthcare experts to explore the impact of different explanations on trust, understandability and model improvement. Our results reveal the insufficiency of global model-centric explanations for guiding users during data configuration. Although data-centric explanations enhanced understanding of post-configuration system changes, a hybrid fusion of both explanation types demonstrated the highest effectiveness. Based on our study results, we also present design implications for effective explanation-driven interactive machine-learning systems.

Riccardo Volpato, Simone Stumpf, Lisa DeBruine

People are increasingly turning to generative AI (e.g., ChatGPT, Gemini, Copilot) for emotional support and companionship. While trust is likely to play a central role in enabling these informal and unsupervised interactions, we still lack an understanding of how people develop and experience it in this context. Seeking to fill this gap, we recruited 24 frequent users of generative AI for emotional support and conducted a qualitative study consisting of diary entries about interactions, transcripts of chats with AI, and in-depth interviews. Our results suggest important novel drivers of trust in this context: familiarity emerging from personalisation, nuanced mental models of generative AI, and awareness of people's control over conversations. Notably, generative AI's homogeneous use of personalised, positive, and persuasive language appears to promote some of these trust-building factors. However, this also seems to discourage other trust-related behaviours, such as remembering that generative AI is a machine trained to converse in human language. We present implications for future research that are likely to become critical as the use of generative AI for emotional support increasingly overlaps with therapeutic work.

Aditya Bhattacharya, Simone Stumpf, Katrien Verbert

With the increasing adoption of Artificial Intelligence (AI) systems in high-stake domains, such as healthcare, effective collaboration between domain experts and AI is imperative. To facilitate effective collaboration between domain experts and AI systems, we introduce an Explanatory Model Steering system that allows domain experts to steer prediction models using their domain knowledge. The system includes an explanation dashboard that combines different types of data-centric and model-centric explanations and allows prediction models to be steered through manual and automated data configuration approaches. It allows domain experts to apply their prior knowledge for configuring the underlying training data and refining prediction models. Additionally, our model steering system has been evaluated for a healthcare-focused scenario with 174 healthcare experts through three extensive user studies. Our findings highlight the importance of involving domain experts during model steering, ultimately leading to improved human-AI collaboration.

Aditya Bhattacharya, Simone Stumpf, Robin De Croon et al.

Representation bias is one of the most common types of biases in artificial intelligence (AI) systems, causing AI models to perform poorly on underrepresented data segments. Although AI practitioners use various methods to reduce representation bias, their effectiveness is often constrained by insufficient domain knowledge in the debiasing process. To address this gap, this paper introduces a set of generic design guidelines for effectively involving domain experts in representation debiasing. We instantiated our proposed guidelines in a healthcare-focused application and evaluated them through a comprehensive mixed-methods user study with 35 healthcare experts. Our findings show that involving domain experts can reduce representation bias without compromising model accuracy. Based on our findings, we also offer recommendations for developers to build robust debiasing systems guided by our generic design guidelines, ensuring more effective inclusion of domain experts in the debiasing process.

Evdoxia Taka, Yuri Nakao, Ryosuke Sonoda et al.

Fairness is a growing concern for high-risk decision-making using Artificial Intelligence (AI) but ensuring it through purely technical means is challenging: there is no universally accepted fairness measure, fairness is context-dependent, and there might be conflicting perspectives on what is considered fair. Thus, involving stakeholders, often without a background in AI or fairness, is a promising avenue. Research to directly involve stakeholders is in its infancy, and many questions remain on how to support stakeholders to feedback on fairness, and how this feedback can be integrated into AI models. Our work follows an approach where stakeholders can give feedback on specific decision instances and their outcomes with respect to their fairness, and then to retrain an AI model. In order to investigate this approach, we conducted two studies of a complex AI model for credit rating used in loan applications. In study 1, we collected feedback from 58 lay users on loan application decisions, and conducted offline experiments to investigate the effects on accuracy and fairness metrics. In study 2, we deepened this investigation by showing 66 participants the results of their feedback with respect to fairness, and then conducted further offline analyses. Our work contributes two datasets and associated code frameworks to bootstrap further research, highlights the opportunities and challenges of employing lay user feedback for improving AI fairness, and discusses practical implications for developing AI applications that more closely reflect stakeholder views about fairness.

Lin Luo, Yuri Nakao, Mathieu Chollet et al.

Assessing fairness in artificial intelligence (AI) typically involves AI experts who select protected features, fairness metrics, and set fairness thresholds. However, little is known about how stakeholders, particularly those affected by AI outcomes but lacking AI expertise, assess fairness. To address this gap, we conducted a qualitative study with 30 stakeholders without AI expertise, representing potential decision subjects in a credit rating scenario, to examine how they assess fairness when placed in the role of deciding on features with priority, metrics, and thresholds. We reveal that stakeholders' fairness decisions are more complex than typical AI expert practices: they considered features far beyond legally protected features, tailored metrics for specific contexts, set diverse yet stricter fairness thresholds, and even preferred designing customized fairness. Our results extend the understanding of how stakeholders can meaningfully contribute to AI fairness governance and mitigation, underscoring the importance of incorporating stakeholders' nuanced fairness judgments.

Christopher Mendez, Lara Letaw, Margaret Burnett et al.

How can software practitioners assess whether their software supports diverse users? Although there are empirical processes that can be used to find "inclusivity bugs" piecemeal, what is often needed is a systematic inspection method to assess soft-ware's support for diverse populations. To help fill this gap, this paper introduces InclusiveMag, a generalization of GenderMag that can be used to generate systematic inclusiveness methods for a particular dimension of diversity. We then present a multi-case study covering eight diversity dimensions, of eight teams' experiences applying InclusiveMag to eight under-served populations and their "mainstream" counterparts.