Research Papers

The rapid development of generative artificial intelligence (AI) technologies raises concerns about the accountability of sociotechnical systems. Current generative AI systems rely on complex mechanisms that make it difficult for even experts to fully trace the reasons behind the outputs. This paper first examines existing research on AI transparency and accountability and argues that transparency is not a sufficient condition for accountability but can contribute to its improvement. We then discuss that if it is not possible to make generative AI transparent, generative AI technology becomes ``artificially created nature'' in a metaphorical sense, and suggest using the precautionary principle approach to consider AI risks. Finally, we propose that a platform for citizen participation is needed to address the risks of generative AI.

AI safety has emerged as a critical priority as these systems are increasingly deployed in real-world applications. We propose the first domain-agnostic AI safety ensuring framework that achieves strong safety guarantees while preserving high performance, grounded in rigorous theoretical foundations. Our framework includes: (1) an optimization component with chance constraints, (2) a safety classification model, (3) internal test data, (4) conservative testing procedures, (5) informative dataset quality measures, and (6) continuous approximate loss functions with gradient computation. Furthermore, to our knowledge, we mathematically establish the first scaling law in AI safety research, relating data quantity to safety-performance trade-offs. Experiments across reinforcement learning, natural language generation, and production planning validate our framework and demonstrate superior performance. Notably, in reinforcement learning, we achieve 3 collisions during 10M actions, compared with 1,000-3,000 for PPO-Lag baselines at equivalent performance levels -- a safety level unattainable by previous AI methods. We believe our framework opens a new foundation for safe AI deployment across safety-critical domains.

While analysing challenges in pilot projects developing AI with marginalized communities, we found it difficult to express them within commonly used paradigms. We therefore constructed an alternative conceptual framework to ground AI development in the social fabric -- the Cloud Weaving Model -- inspired (amongst others) by indigenous knowledge, motifs from nature, and Eastern traditions. This paper introduces and elaborates on the fundamental elements of the model (clouds, spiders, threads, spiderwebs, and weather) and their interpretation in an AI context. The framework is then applied to comprehend patterns observed in co-creation pilots approaching marginalized communities, highlighting neglected yet relevant dimensions for responsible AI development.

With artificial intelligence (AI) embedded in many everyday software systems, effectively and reliably developing and maintaining AI systems becomes an essential skill for software developers. However, the complexity inherent to AI poses new challenges. Explainable AI (XAI) may allow developers to understand better the systems they build, which, in turn, can help with tasks like debugging. In this paper, we report insights from a series of surveys with software developers that highlight that there is indeed an increased need for explanatory tools to support developers in creating AI systems. However, the feedback also indicates that existing XAI systems still fall short of this aspiration. Thus, we see an unmet need to provide developers with adequate support mechanisms to cope with this complexity so they can embed AI into high-quality software in the future.

Fairness in artificial intelligence (AI) prediction models is increasingly emphasized to support responsible adoption in high-stakes domains such as health care and criminal justice. Guidelines and implementation frameworks highlight the importance of both predictive accuracy and equitable outcomes. However, current fairness toolkits often evaluate classification performance disparities in isolation, with limited attention to other critical aspects such as calibration. To address these gaps, we present seeBias, an R package for comprehensive evaluation of model fairness and predictive performance. seeBias offers an integrated evaluation across classification, calibration, and other performance domains, providing a more complete view of model behavior. It includes customizable visualizations to support transparent reporting and responsible AI implementation. Using public datasets from criminal justice and healthcare, we demonstrate how seeBias supports fairness evaluations, and uncovers disparities that conventional fairness metrics may overlook. The R package is available on GitHub, and a Python version is under development.

Deep learning models have achieved impressive performance in medical image segmentation, yet their black-box nature limits clinical adoption. In vascular applications, trustworthy segmentation should rely on both local image cues and global anatomical structures, such as vessel connectivity or branching. However, the extent to which models leverage such global context remains unclear. We present a novel explainability pipeline for 3D vessel segmentation, combining gradient-based attribution with graph-guided point selection and a blob-based analysis of Saliency maps. Using vascular graphs extracted from ground truth, we define anatomically meaningful points of interest (POIs) and assess the contribution of input voxels via Saliency maps. These are analyzed at both global and local scales using a custom blob detector. Applied to IRCAD and Bullitt datasets, our analysis shows that model decisions are dominated by highly localized attribution blobs centered near POIs. Attribution features show little correlation with vessel-level properties such as thickness, tubularity, or connectivity -- suggesting limited use of global anatomical reasoning. Our results underline the importance of structured explainability tools and highlight the current limitations of segmentation models in capturing global vascular context.

Beyond Feature Importance: Feature Interactions in Predicting Post-Stroke Rigidity with Graph Explainable AI

Jiawei Xu, Yonggeon Lee, Anthony Elkommos Youssef +6

This study addresses the challenge of predicting post-stroke rigidity by emphasizing feature interactions through graph-based explainable AI. Post-stroke rigidity, characterized by increased muscle tone and stiffness, significantly affects survivors' mobility and quality of life. Despite its prevalence, early prediction remains limited, delaying intervention. We analyze 519K stroke hospitalization records from the Healthcare Cost and Utilization Project dataset, where 43% of patients exhibited rigidity. We compare traditional approaches such as Logistic Regression, XGBoost, and Transformer with graph-based models like Graphormer and Graph Attention Network. These graph models inherently capture feature interactions and incorporate intrinsic or post-hoc explainability. Our results show that graph-based methods outperform others (AUROC 0.75), identifying key predictors such as NIH Stroke Scale and APR-DRG mortality risk scores. They also uncover interactions missed by conventional models. This research provides a novel application of graph-based XAI in stroke prognosis, with potential to guide early identification and personalized rehabilitation strategies.

Artificial intelligence-augmented technology represents a considerable opportunity for improving healthcare delivery. Significant progress has been made to demonstrate the value of complex models to enhance clinicians` efficiency in decision-making. However, the clinical adoption of such models is scarce due to multifaceted implementation issues, with the explainability of AI models being among them. One of the substantially documented areas of concern is the unclear AI explainability that negatively influences clinicians` considerations for accepting the complex model. With a usability study engaging 20 U.S.-based clinicians and following the qualitative reflexive thematic analysis, this study develops and presents a concrete framework and an operational definition of explainability. The framework can inform the required customizations and feature developments in AI tools to support clinicians` preferences and enhance their acceptance.

Recommender systems have become an integral part of our daily online experience by analyzing past user behavior to suggest relevant content in entertainment domains such as music, movies, and books. Today, they are among the most widely used applications of AI and machine learning. Consequently, regulations and guidelines for trustworthy AI, such as the European AI Act, which addresses issues like bias and fairness, are highly relevant to the design, development, and evaluation of recommender systems. One particularly important type of bias in this context is popularity bias, which results in the unfair underrepresentation of less popular content in recommendation lists. This work summarizes our research on investigating the amplification of popularity bias in recommender systems within the entertainment sector. Analyzing datasets from three entertainment domains, music, movies, and anime, we demonstrate that an item's recommendation frequency is positively correlated with its popularity. As a result, user groups with little interest in popular content receive less accurate recommendations compared to those who prefer widely popular items. Furthermore, this work contributes to a better understanding of the connection between recommendation accuracy, calibration quality of algorithms, and popularity bias amplification.

Generative Pre-trained Transformers (GPTs), particularly Large Language Models (LLMs) like ChatGPT, have proven effective in content generation and productivity enhancement. However, legal risks associated with these tools lead to adoption variance and concealment of AI use within organizations. This study examines the impact of disclosure on ChatGPT adoption in legal, audit and advisory roles in consulting firms through the lens of agency theory. We conducted a survey experiment to evaluate agency costs in the context of unregulated corporate use of ChatGPT, with a particular focus on how mandatory disclosure influences information asymmetry and misaligned interests. Our findings indicate that in the absence of corporate regulations, such as an AI policy, firms may incur agency costs, which can hinder the full benefits of GPT adoption. While disclosure policies reduce information asymmetry, they do not significantly lower overall agency costs due to managers undervaluing analysts' contributions with GPT use. Finally, we examine the scope of existing regulations in Europe and the United States regarding disclosure requirements, explore the sharing of risk and responsibility within firms, and analyze how incentive mechanisms promote responsible AI adoption.

Additive feature explanations rely primarily on game-theoretic notions such as the Shapley value by viewing features as cooperating players. The Shapley value's popularity in and outside of explainable AI stems from its axiomatic uniqueness. However, its computational complexity severely limits practicability. Most works investigate the uniform approximation of all features' Shapley values, needlessly consuming samples for insignificant features. In contrast, identifying the $k$ most important features can already be sufficiently insightful and yields the potential to leverage algorithmic opportunities connected to the field of multi-armed bandits. We propose Comparable Marginal Contributions Sampling (CMCS), a method for the top-$k$ identification problem utilizing a new sampling scheme taking advantage of correlated observations. We conduct experiments to showcase the efficacy of our method in compared to competitive baselines. Our empirical findings reveal that estimation quality for the approximate-all problem does not necessarily transfer to top-$k$ identification and vice versa.

Image classification models trained on clean data often degrade sharply when exposed to corrupted test or deployment data, such as images with impulse noise, Gaussian noise, or environmental noise. This degradation reduces overall performance and disproportionately affects demographic subgroups, raising algorithmic bias concerns. Although robust learning algorithms such as Sharpness-Aware Minimization improve overall robustness and generalization, they do not address biased performance degradation across demographic subgroups. Existing fairness-aware machine learning methods reduce performance disparities but struggle to maintain robust and equitable accuracy across demographic subgroups under data corruption. This limitation reveals an inherent tension between robustness and fairness under corrupted data. To address these challenges, we introduce a metric to assess performance degradation across subgroups under data corruption. We propose FairSAM, a framework that integrates Fairness-oriented strategies into SAM to equalize performance across demographic groups under corrupted conditions. Experiments on multiple real-world datasets and prediction tasks show that FairSAM balances robustness and fairness in corrupted image classification. The framework yields a structured solution for fair and robust image classification in the presence of data corruption.