Research Papers

A plethora of toolkits, checklists, and workshops have been developed to bridge the well-documented gap between AI ethics principles and practice. Yet little is known about effects of such interventions on practitioners. We conducted an ethnographic investigation in a major European city organization that developed and works to integrate an ethics toolkit into city operations. We find that the integration of ethics tools by technical teams destabilises their boundaries, roles, and mandates around responsibilities and decisions. This lead to emotional discomfort and feelings of vulnerability, which neither toolkit designers nor the organization had accounted for. We leverage the concept of moral stress to argue that this affective experience is a core challenge to the successful integration of ethics tools in technical practice. Even in this best case scenario, organisational structures were not able to deal with moral stress that resulted from attempts to implement responsible technology development practices.

Mind the Gesture: Evaluating AI Sensitivity to Culturally Offensive Non-Verbal Gestures

Akhila Yerukola, Saadia Gabriel, Nanyun Peng +1

Gestures are an integral part of non-verbal communication, with meanings that vary across cultures, and misinterpretations that can have serious social and diplomatic consequences. As AI systems become more integrated into global applications, ensuring they do not inadvertently perpetuate cultural offenses is critical. To this end, we introduce Multi-Cultural Set of Inappropriate Gestures and Nonverbal Signs (MC-SIGNS), a dataset of 288 gesture-country pairs annotated for offensiveness, cultural significance, and contextual factors across 25 gestures and 85 countries. Through systematic evaluation using MC-SIGNS, we uncover critical limitations: text-to-image (T2I) systems exhibit strong US-centric biases, performing better at detecting offensive gestures in US contexts than in non-US ones; large language models (LLMs) tend to over-flag gestures as offensive; and vision-language models (VLMs) default to US-based interpretations when responding to universal concepts like wishing someone luck, frequently suggesting culturally inappropriate gestures. These findings highlight the urgent need for culturally-aware AI safety mechanisms to ensure equitable global deployment of AI technologies.

Conversational Explanations: Discussing Explainable AI with Non-AI Experts

Tong Zhang, Mengao Zhang, Wei Yan Low +2

Explainable AI (XAI) aims to provide insights into the decisions made by AI models. To date, most XAI approaches provide only one-time, static explanations, which cannot cater to users' diverse knowledge levels and information needs. Conversational explanations have been proposed as an effective method to customize XAI explanations. However, building conversational explanation systems is hindered by the scarcity of training data. Training with synthetic data faces two main challenges: lack of data diversity and hallucination in the generated data. To alleviate these issues, we introduce a repetition penalty to promote data diversity and exploit a hallucination detector to filter out untruthful synthetic conversation turns. We conducted both automatic and human evaluations on the proposed system, fEw-shot Multi-round ConvErsational Explanation (EMCEE). For automatic evaluation, EMCEE achieves relative improvements of 81.6% in BLEU and 80.5% in ROUGE compared to the baselines. EMCEE also mitigates the degeneration of data quality caused by training on synthetic data. In human evaluations (N=60), EMCEE outperforms baseline models and the control group in improving users' comprehension, acceptance, trust, and collaboration with static explanations by large margins. Through a fine-grained analysis of model responses, we further demonstrate that training on self-generated synthetic data improves the model's ability to generate more truthful and understandable answers, leading to better user interactions. To the best of our knowledge, this is the first conversational explanation method that can answer free-form user questions following static explanations.

Deep learning-based medical image segmentation models, such as U-Net, rely on high-quality annotated datasets to achieve accurate predictions. However, the increasing use of generative models for synthetic data augmentation introduces potential risks, particularly in the absence of rigorous quality control. In this paper, we investigate the impact of synthetic MRI data on the robustness and segmentation accuracy of U-Net models for brain tumor segmentation. Specifically, we generate synthetic T1-contrast-enhanced (T1-Ce) MRI scans using a GAN-based model with a shared encoding-decoding framework and shortest-path regularization. To quantify the effect of synthetic data contamination, we train U-Net models on progressively "poisoned" datasets, where synthetic data proportions range from 16.67% to 83.33%. Experimental results on a real MRI validation set reveal a significant performance degradation as synthetic data increases, with Dice coefficients dropping from 0.8937 (33.33% synthetic) to 0.7474 (83.33% synthetic). Accuracy and sensitivity exhibit similar downward trends, demonstrating the detrimental effect of synthetic data on segmentation robustness. These findings underscore the importance of quality control in synthetic data integration and highlight the risks of unregulated synthetic augmentation in medical image analysis. Our study provides critical insights for the development of more reliable and trustworthy AI-driven medical imaging systems.

The EU AI Act underscores the importance of transparency, user-centricity, and robustness in AI systems, particularly for high-risk systems. In response, we present advancements in XentricAI, an explainable hand gesture recognition (HGR) system designed to meet these regulatory requirements. XentricAI adresses fundamental challenges in HGR, such as the opacity of black-box models using explainable AI methods and the handling of distributional shifts in real-world data through transfer learning techniques. We extend an existing radar-based HGR dataset by adding 28,000 new gestures, with contributions from multiple users across varied locations, including 24,000 out-of-distribution gestures. Leveraging this real-world dataset, we enhance XentricAI's capabilities by integrating a variational autoencoder module for improved gesture anomaly detection, incorporating user-specific thresholding. This integration enables the identification of 11.50% more anomalous gestures. Our extensive evaluations demonstrate a 97.5% sucess rate in characterizing these anomalies, significantly improving system explainability. Furthermore, the implementation of transfer learning techniques has shown a substantial increase in user adaptability, with an average improvement of at least 15.17%. This work contributes to the development of trustworthy AI systems by providing both technical advancements and regulatory compliance, offering a commercially viable solution that aligns with the EU AI Act requirements.

This paper argues that market governance mechanisms should be considered a key approach in the governance of artificial intelligence (AI), alongside traditional regulatory frameworks. While current governance approaches have predominantly focused on regulation, we contend that market-based mechanisms offer effective incentives for responsible AI development. We examine four emerging vectors of market governance: insurance, auditing, procurement, and due diligence, demonstrating how these mechanisms can affirm the relationship between AI risk and financial risk while addressing capital allocation inefficiencies. While we do not claim that market forces alone can adequately protect societal interests, we maintain that standardised AI disclosures and market mechanisms can create powerful incentives for safe and responsible AI development. This paper urges regulators, economists, and machine learning researchers to investigate and implement market-based approaches to AI governance.

The potential for negative impacts of AI has rapidly become more pervasive around the world, and this has intensified a need for responsible AI governance. While many regulatory bodies endorse risk-based approaches and a multitude of risk mitigation practices are proposed by companies and academic scholars, these approaches are commonly expert-centered and thus lack the inclusion of a significant group of stakeholders. Ensuring that AI policies align with democratic expectations requires methods that prioritize the voices and needs of those impacted. In this work we develop a participative and forward-looking approach to inform policy-makers and academics that grounds the needs of lay stakeholders at the forefront and enriches the development of risk mitigation strategies. Our approach (1) maps potential mitigation and prevention strategies of negative AI impacts that assign responsibility to various stakeholders, (2) explores the importance and prioritization thereof in the eyes of laypeople, and (3) presents these insights in policy fact sheets, i.e., a digestible format for informing policy processes. We emphasize that this approach is not targeted towards replacing policy-makers; rather our aim is to present an informative method that enriches mitigation strategies and enables a more participatory approach to policy development.

AI Safety Moderation (ASM) classifiers are designed to moderate content on social media platforms and to serve as guardrails that prevent Large Language Models (LLMs) from being fine-tuned on unsafe inputs. Owing to their potential for disparate impact, it is crucial to ensure that these classifiers: (1) do not unfairly classify content belonging to users from minority groups as unsafe compared to those from majority groups and (2) that their behavior remains robust and consistent across similar inputs. In this work, we thus examine the fairness and robustness of four widely-used, closed-source ASM classifiers: OpenAI Moderation API, Perspective API, Google Cloud Natural Language (GCNL) API, and Clarifai API. We assess fairness using metrics such as demographic parity and conditional statistical parity, comparing their performance against ASM models and a fair-only baseline. Additionally, we analyze robustness by testing the classifiers' sensitivity to small and natural input perturbations. Our findings reveal potential fairness and robustness gaps, highlighting the need to mitigate these issues in future versions of these models.

As artificial intelligence systems become increasingly integrated into daily life, the field of explainability has gained significant attention. This trend is particularly driven by the complexity of modern AI models and their decision-making processes. The advent of foundation models, characterized by their extensive generalization capabilities and emergent uses, has further complicated this landscape. Foundation models occupy an ambiguous position in the explainability domain: their complexity makes them inherently challenging to interpret, yet they are increasingly leveraged as tools to construct explainable models. In this survey, we explore the intersection of foundation models and eXplainable AI (XAI) in the vision domain. We begin by compiling a comprehensive corpus of papers that bridge these fields. Next, we categorize these works based on their architectural characteristics. We then discuss the challenges faced by current research in integrating XAI within foundation models. Furthermore, we review common evaluation methodologies for these combined approaches. Finally, we present key observations and insights from our survey, offering directions for future research in this rapidly evolving field.

This paper proposes a method for measuring conditional feature importance via generative modeling. In explainable artificial intelligence (XAI), conditional feature importance assesses the impact of a feature on a prediction model's performance given the information of other features. Model-agnostic post hoc methods to do so typically evaluate changes in the predictive performance under on-manifold feature value manipulations. Such procedures require creating feature values that respect conditional feature distributions, which can be challenging in practice. Recent advancements in generative modeling can facilitate this. For tabular data, which may consist of both categorical and continuous features, the adversarial random forest (ARF) stands out as a generative model that can generate on-manifold data points without requiring intensive tuning efforts or computational resources, making it a promising candidate model for subroutines in XAI methods. This paper proposes cARFi (conditional ARF feature importance), a method for measuring conditional feature importance through feature values sampled from ARF-estimated conditional distributions. cARFi requires only little tuning to yield robust importance scores that can flexibly adapt for conditional or marginal notions of feature importance, including straightforward extensions to condition on feature subsets and allows for inferring the significance of feature importances through statistical tests.

This study introduces an integrated approach to recognizing Arabic Sign Language (ArSL) using state-of-the-art deep learning models such as MobileNetV3, ResNet50, and EfficientNet-B2. These models are further enhanced by explainable AI (XAI) techniques to boost interpretability. The ArSL2018 and RGB Arabic Alphabets Sign Language (AASL) datasets are employed, with EfficientNet-B2 achieving peak accuracies of 99.48\% and 98.99\%, respectively. Key innovations include sophisticated data augmentation methods to mitigate class imbalance, implementation of stratified 5-fold cross-validation for better generalization, and the use of Grad-CAM for clear model decision transparency. The proposed system not only sets new benchmarks in recognition accuracy but also emphasizes interpretability, making it suitable for applications in healthcare, education, and inclusive communication technologies.

Explainable AI (XAI) in medical histopathology is essential for enhancing the interpretability and clinical trustworthiness of deep learning models in cancer diagnosis. However, the black-box nature of these models often limits their clinical adoption. We introduce GRAPHITE (Graph-based Interpretable Tissue Examination), a post-hoc explainable framework designed for breast cancer tissue microarray (TMA) analysis. GRAPHITE employs a multiscale approach, extracting patches at various magnification levels, constructing an hierarchical graph, and utilising graph attention networks (GAT) with scalewise attention (SAN) to capture scale-dependent features. We trained the model on 140 tumour TMA cores and four benign whole slide images from which 140 benign samples were created, and tested it on 53 pathologist-annotated TMA samples. GRAPHITE outperformed traditional XAI methods, achieving a mean average precision (mAP) of 0.56, an area under the receiver operating characteristic curve (AUROC) of 0.94, and a threshold robustness (ThR) of 0.70, indicating that the model maintains high performance across a wide range of thresholds. In clinical utility, GRAPHITE achieved the highest area under the decision curve (AUDC) of 4.17e+5, indicating reliable decision support across thresholds. These results highlight GRAPHITE's potential as a clinically valuable tool in computational pathology, providing interpretable visualisations that align with the pathologists' diagnostic reasoning and support precision medicine.