Research Papers

Explainable AI (XAI) provides methods to understand non-interpretable machine learning models. However, we have little knowledge about what legal experts expect from these explanations, including their legal compliance with, and value against European Union legislation. To close this gap, we present the Explanation Dialogues, an expert focus study to uncover the expectations, reasoning, and understanding of legal experts and practitioners towards XAI, with a specific focus on the European General Data Protection Regulation. The study consists of an online questionnaire and follow-up interviews, and is centered around a use-case in the credit domain. We extract both a set of hierarchical and interconnected codes using grounded theory, and present the standpoints of the participating experts towards XAI. We find that the presented explanations are hard to understand and lack information, and discuss issues that can arise from the different interests of the data controller and subject. Finally, we present a set of recommendations for developers of XAI methods, and indications of legal areas of discussion. Among others, recommendations address the presentation, choice, and content of an explanation, technical risks as well as the end-user, while we provide legal pointers to the contestability of explanations, transparency thresholds, intellectual property rights as well as the relationship between involved parties.

AI systems are increasingly deployed in both public and private sectors to independently make complicated decisions with far-reaching impact on individuals and the society. However, many AI algorithms are biased in the collection or processing of data, resulting in prejudiced decisions based on demographic features. Algorithmic biases occur because of the training data fed into the AI system or the design of algorithmic models. While most legal scholars propose a direct-regulation approach associated with the right of explanation or transparency obligation, this article provides a different picture regarding how indirect regulation can be used to regulate algorithmic bias based on the New Chicago School framework developed by Lawrence Lessig. This article concludes that an effective regulatory approach toward algorithmic bias will be the right mixture of direct and indirect regulations through architecture, norms, market, and the law.

Explaining the results of clustering pipelines by unraveling the characteristics of each cluster is a challenging task, often addressed manually through visualizations and queries. Existing solutions from the domain of Explainable Artificial Intelligence (XAI) are largely ineffective for cluster explanations, and interpretable-by-design clustering algorithms may be unsuitable when the clustering algorithm does not fit the data properties. To bridge this gap, we introduce Cluster-Explorer, a novel explainability tool for black-box clustering pipelines. Our approach formulates the explanation of clusters as the identification of concise conjunctions of predicates that maximize the coverage of the cluster's data points while minimizing separation from other clusters. We achieve this by reducing the problem to generalized frequent-itemsets mining (gFIM), where items correspond to explanation predicates, and itemset frequency indicates coverage. To enhance efficiency, we leverage inherent problem properties and implement attribute selection to further reduce computational costs. Experimental evaluations on a benchmark collection of 98 clustering results, as well as a user study, demonstrate the superiority of Cluster-Explorer in both explanation quality and execution times compared to XAI baselines.

Artificial Intelligence (AI) has emerged as a key technology, driving advancements across a range of applications. Its integration into modern autonomous systems requires assuring safety. However, the challenge of assuring safety in systems that incorporate AI components is substantial. The lack of concrete specifications, and also the complexity of both the operational environment and the system itself, leads to various aspects of uncertain behavior and complicates the derivation of convincing evidence for system safety. Nonetheless, scholars proposed to thoroughly analyze and mitigate AI-specific insufficiencies, so-called AI safety concerns, which yields essential evidence supporting a convincing assurance case. In this paper, we build upon this idea and propose the so-called Landscape of AI Safety Concerns, a novel methodology designed to support the creation of safety assurance cases for AI-based systems by systematically demonstrating the absence of AI safety concerns. The methodology's application is illustrated through a case study involving a driverless regional train, demonstrating its practicality and effectiveness.

Recent research illustrates how AI can be developed and deployed in a manner detached from the concrete social context of application. By abstracting from the contexts of AI application, practitioners also disengage from the distinct normative structures that govern them. Building upon Helen Nissenbaum's framework of contextual integrity, I illustrate how disregard for contextual norms can threaten the integrity of a context with often decisive ethical implications. I argue that efforts to promote responsible and ethical AI can inadvertently contribute to and seemingly legitimize this disregard for established contextual norms. Echoing a persistent undercurrent in technology ethics of understanding emerging technologies as uncharted moral territory, certain approaches to AI ethics can promote a notion of AI as a novel and distinct realm for ethical deliberation, norm setting, and virtue cultivation. This narrative of AI as new ethical ground, however, can come at the expense of practitioners, policymakers and ethicists engaging with already established norms and virtues that were gradually cultivated to promote successful and responsible practice within concrete social contexts. In response, I question the current narrow prioritization in AI ethics of moral innovation over moral preservation. Engaging also with emerging foundation models, I advocate for a moderately conservative approach to the ethics of AI that prioritizes the responsible and considered integration of AI within established social contexts and their respective normative structures.

This report presents a comprehensive response to the United Nation's Interim Report on Governing Artificial Intelligence (AI) for Humanity. It emphasizes the transformative potential of AI in achieving the Sustainable Development Goals (SDGs) while acknowledging the need for robust governance to mitigate associated risks. The response highlights opportunities for promoting equitable, secure, and inclusive AI ecosystems, which should be supported by investments in infrastructure and multi-stakeholder collaborations across jurisdictions. It also underscores challenges, including societal inequalities exacerbated by AI, ethical concerns, and environmental impacts. Recommendations advocate for legally binding norms, transparency, and multi-layered data governance models, alongside fostering AI literacy and capacity-building initiatives. Internationally, the report calls for harmonising AI governance frameworks with established laws, human rights standards, and regulatory approaches. The report concludes with actionable principles for fostering responsible AI governance through collaboration among governments, industry, academia, and civil society, ensuring the development of AI aligns with universal human values and the public good.

SPES: Spectrogram Perturbation for Explainable Speech-to-Text Generation

Dennis Fucci, Marco Gaido, Beatrice Savoldi +3

Spurred by the demand for interpretable models, research on eXplainable AI for language technologies has experienced significant growth, with feature attribution methods emerging as a cornerstone of this progress. While prior work in NLP explored such methods for classification tasks and textual applications, explainability intersecting generation and speech is lagging, with existing techniques failing to account for the autoregressive nature of state-of-the-art models and to provide fine-grained, phonetically meaningful explanations. We address this gap by introducing Spectrogram Perturbation for Explainable Speech-to-text Generation (SPES), a feature attribution technique applicable to sequence generation tasks with autoregressive models. SPES provides explanations for each predicted token based on both the input spectrogram and the previously generated tokens. Extensive evaluation on speech recognition and translation demonstrates that SPES generates explanations that are faithful and plausible to humans.

With rapid transformation of technologies, the fusion of Artificial Intelligence (AI) and Machine Learning (ML) in finance is disrupting the entire ecosystem and operations which were followed for decades. The current landscape is where decisions are increasingly data-driven by financial institutions with an appetite for automation while mitigating risks. The segments of financial institutions which are getting heavily influenced are retail banking, wealth management, corporate banking & payment ecosystem. The solution ranges from onboarding the customers all the way fraud detection & prevention to enhancing the customer services. Financial Institutes are leap frogging with integration of Artificial Intelligence and Machine Learning in mainstream applications and enhancing operational efficiency through advanced predictive analytics, extending personalized customer experiences, and automation to minimize risk with fraud detection techniques. However, with Adoption of AI & ML, it is imperative that the financial institute also needs to address ethical and regulatory challenges, by putting in place robust governance frameworks and responsible AI practices.

Gene expression analysis is a critical method for cancer classification, enabling precise diagnoses through the identification of unique molecular signatures associated with various tumors. Identifying cancer-specific genes from gene expression values enables a more tailored and personalized treatment approach. However, the high dimensionality of mRNA gene expression data poses challenges for analysis and data extraction. This research presents a comprehensive pipeline designed to accurately identify 33 distinct cancer types and their corresponding gene sets. It incorporates a combination of normalization and feature selection techniques to reduce dataset dimensionality effectively while ensuring high performance. Notably, our pipeline successfully identifies a substantial number of cancer-specific genes using a reduced feature set of just 500, in contrast to using the full dataset comprising 19,238 features. By employing an ensemble approach that combines three top-performing classifiers, a classification accuracy of 96.61% was achieved. Furthermore, we leverage Explainable AI to elucidate the biological significance of the identified cancer-specific genes, employing Differential Gene Expression (DGE) analysis.

The widespread diffusion of Artificial Intelligence (AI)-based systems offers many opportunities to contribute to the well-being of individuals and the advancement of economies and societies. This diffusion is, however, closely accompanied by public scandals causing harm to individuals, markets, or society, and leading to the increasing importance of accountability. AI accountability itself faces conceptual ambiguity, with research scattered across multiple disciplines. To address these issues, we review current research across multiple disciplines and identify key dimensions of accountability in the context of AI. We reveal six themes with 13 corresponding dimensions and additional accountability facilitators that future research can utilize to specify accountability scenarios in the context of AI-based systems.

Wrist pathologies, {particularly fractures common among children and adolescents}, present a critical diagnostic challenge. While X-ray imaging remains a prevalent diagnostic tool, the increasing misinterpretation rates highlight the need for more accurate analysis, especially considering the lack of specialized training among many surgeons and physicians. Recent advancements in deep convolutional neural networks offer promise in automating pathology detection in trauma X-rays. However, distinguishing subtle variations between {pediatric} wrist pathologies in X-rays remains challenging. Traditional manual annotation, though effective, is laborious, costly, and requires specialized expertise. {In this paper, we address the challenge of pediatric wrist pathology recognition with a fine-grained approach, aimed at automatically identifying discriminative regions in X-rays without manual intervention. We refine our fine-grained architecture through ablation analysis and the integration of LION.} Leveraging Grad-CAM, an explainable AI technique, we highlight these regions. Despite using limited data, reflective of real-world medical study constraints, our method consistently outperforms state-of-the-art image recognition models on both augmented and original (challenging) test sets. {Our proposed refined architecture achieves an increase in accuracy of 1.06% and 1.25% compared to the baseline method, resulting in accuracies of 86% and 84%, respectively. Moreover, our approach demonstrates the highest fracture sensitivity of 97%, highlighting its potential to enhance wrist pathology recognition. The implementation code can be found at https://github.com/ammarlodhi255/fine-grained-approach-to-wrist-pathology-recognition

Recently, Meta has shifted towards AI-mediated ad targeting mechanisms that do not require advertisers to provide detailed targeting criteria, likely driven by excitement over AI capabilities as well as new data privacy policies and targeting changes agreed upon in civil rights settlements. At the same time, Meta has touted their ad preference controls as an effective mechanism for users to control the ads they see. Furthermore, Meta markets their targeting explanations as a transparency tool that allows users to understand why they saw certain ads and inform actions to control future ads. Our study evaluates the effectiveness of Meta's "See less" ad control and the actionability of ad targeting explanations following the shift to AI-mediated targeting. We conduct a large-scale study, randomly assigning participants to mark "See less" to Body Weight Control or Parenting topics, and collecting the ads and targeting explanations Meta shows to participants before and after the intervention. We find that utilizing the "See less" ad control for the topics we study does not significantly reduce the number of ads shown by Meta on these topics, and that the control is less effective for some users whose demographics are correlated with the topic. Furthermore, we find that the majority of ad targeting explanations for local ads made no reference to location-specific targeting criteria, and did not inform users why ads related to the topics they marked to "See less" of continued to be delivered. We hypothesize that the poor effectiveness of controls and lack of actionability in explanations are the result of the shift to AI-mediated targeting, for which explainability and transparency tools have not yet been developed. Our work thus provides evidence for the need of new methods for transparency and user control, suitable and reflective of increasingly complex AI-mediated ad delivery systems.