There is broad agreement that Artificial Intelligence (AI) systems, particularly those using Machine Learning (ML), should be able to "explain" their behavior. Unfortunately, there is little agreement as to what constitutes an "explanation." This has caused a disconnect between the explanations that systems produce in service of explainable Artificial Intelligence (XAI) and those explanations that users and other audiences actually need, which should be defined by the full spectrum of functional roles, audiences, and capabilities for explanation. In this paper, we explore the features of explanations and how to use those features in evaluating their utility. We focus on the requirements for explanations defined by their functional role, the knowledge states of users who are trying to understand them, and the availability of the information needed to generate them. Further, we discuss the risk of XAI enabling trust in systems without establishing their trustworthiness and define a critical next step for the field of XAI to establish metrics to guide and ground the utility of system-generated explanations.
Simon Fraser University（西蒙弗雷泽大学）；The University of British Columbia（不列颠哥伦比亚大学）
The boundaries of existing explainable artificial intelligence (XAI) algorithms are confined to problems grounded in technical users' demand for explainability. This research paradigm disproportionately ignores the larger group of non-technical end users, who have a much higher demand for AI explanations in diverse explanation goals, such as making safer and better decisions and improving users' predicted outcomes. Lacking explainability-focused functional support for end users may hinder the safe and accountable use of AI in high-stakes domains, such as healthcare, criminal justice, finance, …
In recent years, the field of explainable AI (XAI) has produced a vast collection of algorithms, providing a useful toolbox for researchers and practitioners to build XAI applications. With the rich application opportunities, explainability is believed to have moved beyond a demand by data scientists or researchers to comprehend the models they develop, to an essential requirement for people to trust and adopt AI deployed in numerous domains. However, explainability is an inherently human-centric property and the field is starting to embrace human-centered approaches. Human-computer interactio…
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…
IBM Research AI（IBM研究院AI）；IBM Design（IBM设计）；IBM Research（IBM研究院）
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 according…
Georgia Institute of Technology（佐治亚理工学院）；Microsoft Research（微软研究院）
Explainable AI (XAI) systems are sociotechnical in nature; thus, they are subject to the sociotechnical gap--divide between the technical affordances and the social needs. However, charting this gap is challenging. In the context of XAI, we argue that charting the gap improves our problem understanding, which can reflexively provide actionable insights to improve explainability. Utilizing two case studies in distinct domains, we empirically derive a framework that facilitates systematic charting of the sociotechnical gap by connecting AI guidelines in the context of XAI and elucidating how to …
University of Delhi（德里大学）；RWTH Aachen University（亚琛工业大学）；The University of Sydney（悉尼大学）
In this position paper, we propose building a broader and deeper understanding around Explainability in AI by 'grounding' it in social contexts, the socio-technical systems operate in. We situate our understanding of grounded explainability in the 'Global South' in general and India in particular and express the need for more research within the global south context when it comes to explainability and AI.
Recent years have seen a surge of interest in the field of explainable AI (XAI), with a plethora of algorithms proposed in the literature. However, a lack of consensus on how to evaluate XAI hinders the advancement of the field. We highlight that XAI is not a monolithic set of technologies -- researchers and practitioners have begun to leverage XAI algorithms to build XAI systems that serve different usage contexts, such as model debugging and decision-support. Algorithmic research of XAI, however, often does not account for these diverse downstream usage contexts, resulting in limited effecti…
What Does Evaluation of Explainable Artificial Intelligence Actually Tell Us? A Case for Compositional and Contextual Validation of XAI Building Blocks
False Sense of Security in Explainable Artificial Intelligence (XAI)
Institute of Informatics, University of Warsaw（华沙大学信息学研究所）；School of Law, Seoul National University（首尔国立大学法学院）；Dongin Law Group（东仁法律集团）；Wesang Co., Ltd.（Wesang有限公司）；Informatism LLC（Informatism有限责任公司）
Georgia Institute of Technology（佐治亚理工学院）；IBM Research AI（IBM研究院人工智能部门）
As AI-powered systems increasingly mediate consequential decision-making, their explainability is critical for end-users to take informed and accountable actions. Explanations in human-human interactions are socially-situated. AI systems are often socio-organizationally embedded. However, Explainable AI (XAI) approaches have been predominantly algorithm-centered. We take a developmental step towards socially-situated XAI by introducing and exploring Social Transparency (ST), a sociotechnically informed perspective that incorporates the socio-organizational context into explaining AI-mediated d…
University College Dublin（都柏林大学学院）；Technological University Dublin（都柏林理工大学）；Ho Chi Minh City University of Technology and Education（胡志明市工业大学）；Vellore Institute of Technology（韦洛尔理工学院）；Lebanese American University（黎巴嫩美国大学）
When 5G began its commercialisation journey around 2020, the discussion on the vision of 6G also surfaced. Researchers expect 6G to have higher bandwidth, coverage, reliability, energy efficiency, lower latency, and an integrated "human-centric" network system powered by artificial intelligence (AI). Such a 6G network will lead to an excessive number of automated decisions made in real-time. These decisions can range widely, from network resource allocation to collision avoidance for self-driving cars. However, the risk of losing control over decision-making may increase due to high-speed, dat…
Nanyang Technological University（南洋理工大学）；Alibaba Group Holding Limited（阿里巴巴集团控股有限公司）
Recently, artificial intelligence and machine learning in general have demonstrated remarkable performances in many tasks, from image processing to natural language processing, especially with the advent of deep learning. Along with research progress, they have encroached upon many different fields and disciplines. Some of them require high level of accountability and thus transparency, for example the medical sector. Explanations for machine decisions and predictions are thus needed to justify their reliability. This requires greater interpretability, which often means we need to understand t…
Despite the proliferation of explainable AI (XAI) methods, little is understood about end-users' explainability needs and behaviors around XAI explanations. To address this gap and contribute to understanding how explainability can support human-AI interaction, we conducted a mixed-methods study with 20 end-users of a real-world AI application, the Merlin bird identification app, and inquired about their XAI needs, uses, and perceptions. We found that participants desire practically useful information that can improve their collaboration with the AI, more so than technical system details. Rela…
Pennsylvania State University（宾夕法尼亚州立大学）；College of Information Sciences and Technology（信息科学与技术学院）
Artificial intelligence (AI) has become prevalent in our everyday technologies and impacts both individuals and communities. The explainable AI (XAI) scholarship has explored the philosophical nature of explanation and technical explanations, which are usually driven by experts in lab settings and can be challenging for laypersons to understand. In addition, existing XAI research tends to focus on the individual level. Little is known about how people understand and explain AI-led decisions in the community context. Drawing from XAI and activity theory, a foundational HCI theory, we theorize h…
In recent years, there has been an explosion of AI research on counterfactual explanations as a solution to the problem of eXplainable AI (XAI). These explanations seem to offer technical, psychological and legal benefits over other explanation techniques. We survey 100 distinct counterfactual explanation methods reported in the literature. This survey addresses the extent to which these methods have been adequately evaluated, both psychologically and computationally, and quantifies the shortfalls occurring. For instance, only 21% of these methods have been user tested. Five key deficits in th…
J. P. Morgan AI Research（摩根大通人工智能研究院）；J. P. Morgan（摩根大通）
Regulators have signalled an interest in adopting explainable AI(XAI) techniques to handle the diverse needs for model governance, operational servicing, and compliance in the financial services industry. In this short overview, we review the recent technical literature in XAI and argue that based on our current understanding of the field, the use of XAI techniques in practice necessitate a highly contextualized approach considering the specific needs of stakeholders for particular business applications.
Entropy-Centric Explainable AI for Remote Sensing Image Segmentation
Faculty of Engineering, Lebanese University（黎巴嫩大学工程学院）；University of Paris-Est Créteil (UPEC)（巴黎东部克雷泰伊大学）；EFREI（EFREI学院）；National Center for Remote Sensing - CNRS（国家遥感中心 - 法国国家科学研究中心）
The Contribution of XAI for the Safe Development and Certification of AI: An Expert-Based Analysis
Fraunhofer Institute for Manufacturing Engineering and Automation IPA（弗劳恩霍夫制造工程与自动化研究所 IPA）；University of Stuttgart（斯图加特大学）；Fraunhofer Institute for Industrial Engineering IAO（弗劳恩霍夫工业工程研究所 IAO）
Machine learning (ML) methods can effectively analyse data, recognize patterns in them, and make high-quality predictions. Good predictions usually come along with "black-box" models that are unable to present the detected patterns in a human-readable way. Technical developments recently led to eXplainable Artificial Intelligence (XAI) techniques that aim to open such black-boxes and enable humans to gain new insights from detected patterns. We investigated the application of XAI in an area where specific insights can have a significant effect on consumer behaviour, namely electricity use. Kno…
University of Southern California（南加利福尼亚大学）；Microsoft Research（微软研究院）；IBM Research AI（IBM人工智能研究院）
What does it mean for a generative AI model to be explainable? The emergent discipline of explainable AI (XAI) has made great strides in helping people understand discriminative models. Less attention has been paid to generative models that produce artifacts, rather than decisions, as output. Meanwhile, generative AI (GenAI) technologies are maturing and being applied to application domains such as software engineering. Using scenario-based design and question-driven XAI design approaches, we explore users' explainability needs for GenAI in three software engineering use cases: natural languag…
Mind the XAI Gap: A Human-Centered LLM Framework for Democratizing Explainable AI
Aristotle University of Thessaloniki, School of Informatics（塞萨洛尼基亚里士多德大学信息学院）；Technical University of Denmark（丹麦技术大学）；Telefonica Scientific Research（电信科学研究院）
University College Dublin（都柏林大学学院）；Insight Centre for Data Analytics（Insight数据分析中心）；VistaMilk SFI Research Centre（VistaMilk SFI研究中心）
Recently, a groundswell of research has identified the use of counterfactual explanations as a potentially significant solution to the Explainable AI (XAI) problem. It is argued that (a) technically, these counterfactual cases can be generated by permuting problem-features until a class change is found, (b) psychologically, they are much more causally informative than factual explanations, (c) legally, they are GDPR-compliant. However, there are issues around the finding of good counterfactuals using current techniques (e.g. sparsity and plausibility). We show that many commonly-used datasets …
Ca' Foscari University, Venice, Italy（威尼斯卡弗里大学）；Polytechnic University of Turin, Turin, Italy（都灵理工学院）；European Centre for Living Technology, Venice, Italy（欧洲生活技术中心）；Zhejiang Normal University, Jinhua, China（浙江师范大学）；Denmark Technical University, Lyngby, Denmark（丹麦技术大学）
The increasingly widespread application of AI models motivates increased demand for explanations from a variety of stakeholders. However, this demand is ambiguous because there are many types of 'explanation' with different evaluative criteria. In the spirit of pluralism, I chart a taxonomy of types of explanation and the associated XAI methods that can address them. When we look to expose the inner mechanisms of AI models, we develop Diagnostic-explanations. When we seek to render model output understandable, we produce Explication-explanations. When we wish to form stable generalizations of …
Simon Fraser University（西蒙弗雷泽大学）；The University of British Columbia（不列颠哥伦比亚大学）
Explainable artificial intelligence (XAI) is essential for enabling clinical users to get informed decision support from AI and comply with evidence-based medical practice. Applying XAI in clinical settings requires proper evaluation criteria to ensure the explanation technique is both technically sound and clinically useful, but specific support is lacking to achieve this goal. To bridge the research gap, we propose the Clinical XAI Guidelines that consist of five criteria a clinical XAI needs to be optimized for. The guidelines recommend choosing an explanation form based on Guideline 1 (G1)…
Explainable AI (XAI) research has been booming, but the question "$\textbf{To whom}$ are we making AI explainable?" is yet to gain sufficient attention. Not much of XAI is comprehensible to non-AI experts, who nonetheless, are the primary audience and major stakeholders of deployed AI systems in practice. The gap is glaring: what is considered "explained" to AI-experts versus non-experts are very different in practical scenarios. Hence, this gap produced two distinct cultures of expectations, goals, and forms of XAI in real-life AI deployments. We advocate that it is critical to develop XAI me…
On the Design and Evaluation of Human-centered Explainable AI Systems: A Systematic Review and Taxonomy
Dresden University of Technology（德累斯顿技术大学）；Charité Berlin（柏林夏里特医学院）；Department Speculative Transformation（推测转化部门）；Chair of Engineering Psychology and Applied Cognitive Research（工程心理学与应用认知研究教授职位）
A three-Level Framework for LLM-Enhanced eXplainable AI: From technical explanations to natural language
Andalusian Research Institute in Data Science and Computational Intelligence（数据科学与计算智能安达卢西亚研究机构）；Universidad de Granada（格拉纳达大学）；Department of Computer Science（计算机科学系）；Artificial Intelligence Lab（人工智能实验室）；Vrije Universiteit Brussel（布鲁塞尔自由大学）
Clinically Meaningful Explainability for NeuroAI: An ethical, technical, and clinical perspective
Institute for History and Ethics of Medicine, School of Medicine and Health, Technical University of Munich（医学与健康学院历史与医学伦理研究所，慕尼黑技术大学）；Department of Forensic Psychiatry, Universitätsklinik für Forensische Psychiatrie und Psychologie (FPP), Universitäre Psychiatrische Dienste (UPD) Bern（精神病学系，弗赖堡大学精神病学与心理学诊所（FPP），伯恩大学精神病服务（UPD））
