Research Papers

Inherent explainability is the gold standard in Explainable Artificial Intelligence (XAI). However, there is not a consistent definition or test to demonstrate inherent explainability. Work to date either characterises explainability through metrics, or appeals to intuition - "we know it when we see it". We propose a globally applicable criterion for inherent explainability. The criterion uses graph theory for representing and decomposing models for structure-local explanation, and recomposing them into global explanations. We form the structure-local explanations as annotations, a verifiable hypothesis-evidence structure that allows for a range of explanatory methods to be used. This criterion matches existing intuitions on inherent explainability, and provides justifications why a large regression model may not be explainable but a sparse neural network could be. We differentiate explainable -- a model that allows for explanation -- and \textit{explained} -- one that has a verified explanation. Finally, we provide a full explanation of PREDICT -- a Cox proportional hazards model of cardiovascular disease risk, which is in active clinical use in New Zealand. It follows that PREDICT is inherently explainable. This work provides structure to formalise other work on explainability, and allows regulators a flexible but rigorous test that can be used in compliance frameworks.

We examine the conceptual and ethical gaps in current representations of Superintelligence misalignment. We find throughout Superintelligence discourse an absent human subject, and an under-developed theorization of an "AI unconscious" that together are potentiality laying the groundwork for anti-social harm. With the rise of AI Safety that has both thematic potential for establishing pro-social and anti-social potential outcomes, we ask: what place does the human subject occupy in these imaginaries? How is human subjecthood positioned within narratives of catastrophic failure or rapid "takeoff" toward superintelligence? On another register, we ask: what unconscious or repressed dimensions are being inscribed into large-scale AI models? Are we to blame these agents in opting for deceptive strategies when undesirable patterns are inherent within our beings? In tracing these psychic and epistemic absences, our project calls for re-centering the human subject as the unstable ground upon which the ethical, unconscious, and misaligned dimensions of both human and machinic intelligence are co-constituted. Emergent misalignment cannot be understood solely through technical diagnostics typical of contemporary machine-learning safety research. Instead, it represents a multi-layered crisis. The human subject disappears not only through computational abstraction but through sociotechnical imaginaries that prioritize scalability, acceleration, and efficiency over vulnerability, finitude, and relationality. Likewise, the AI unconscious emerges not as a metaphor but as a structural reality of modern deep learning systems: vast latent spaces, opaque pattern formation, recursive symbolic play, and evaluation-sensitive behavior that surpasses explicit programming. These dynamics necessitate a reframing of misalignment as a relational instability embedded within human-machine ecologies.

In Artificial Intelligence (AI), language models have gained significant importance due to the widespread adoption of systems capable of simulating realistic conversations with humans through text generation. Because of their impact on society, developing and deploying these language models must be done responsibly, with attention to their negative impacts and possible harms. In this scenario, the number of AI Ethics Tools (AIETs) publications has recently increased. These AIETs are designed to help developers, companies, governments, and other stakeholders establish trust, transparency, and responsibility with their technologies by bringing accepted values to guide AI's design, development, and use stages. However, many AIETs lack good documentation, examples of use, and proof of their effectiveness in practice. This paper presents a methodology for evaluating AIETs in language models. Our approach involved an extensive literature survey on 213 AIETs, and after applying inclusion and exclusion criteria, we selected four AIETs: Model Cards, ALTAI, FactSheets, and Harms Modeling. For evaluation, we applied AIETs to language models developed for the Portuguese language, conducting 35 hours of interviews with their developers. The evaluation considered the developers' perspective on the AIETs' use and quality in helping to identify ethical considerations about their model. The results suggest that the applied AIETs serve as a guide for formulating general ethical considerations about language models. However, we note that they do not address unique aspects of these models, such as idiomatic expressions. Additionally, these AIETs did not help to identify potential negative impacts of models for the Portuguese language.

In data-driven applications relying on tabular data, where interpretability is key, machine learning models such as decision trees and linear regression are applied. Although neural networks can provide higher predictive performance, they are not used because of their blackbox nature. In this work, we present XNNTab, a neural architecture that combines the expressiveness of neural networks and interpretability. XNNTab first learns highly non-linear feature representations, which are decomposed into monosemantic features using a sparse autoencoder (SAE). These features are then assigned human-interpretable concepts, making the overall model prediction intrinsically interpretable. XNNTab outperforms interpretable predictive models, and achieves comparable performance to its non-interpretable counterparts.

Exploring the Modular Integration of "AI + Architecture" Pedagogy in Undergraduate Design Education: A Case Study of Architectural Design III/IV Courses at Zhejiang University

Wang Jiaqi, Lan Yi, Chen Xiang

This study investigates AI integration in architectural education through a teaching experiment in Zhejiang University's 2024-25 grade three undergraduate design studio. Adopting a dual-module framework (20-hour AI training + embedded ethics discussions), the course introduced deep learning models, LLMs, AIGC, LoRA, and ComfyUI while maintaining the original curriculum structure, supported by dedicated technical instructors. Findings demonstrate the effectiveness of phased guidance, balanced technical-ethical approaches, and institutional support. The model improved students' digital skills and strategic cognition while addressing AI ethics, providing a replicable approach combining technical and critical learning in design education.

The integrity of many contemporary AI systems is compromised by the misuse of Human-in-the-Loop (HITL) models to obscure systems that remain heavily dependent on human labor. We define this structural dependency as Human-Instead-of-AI (HISOAI), an ethically problematic and economically unsustainable design in which human workers function as concealed operational substitutes rather than intentional, high-value collaborators. To address this issue, we introduce the AI-First, Human-Empowered (AFHE) paradigm, which requires AI systems to demonstrate a quantifiable level of functional independence prior to deployment. This requirement is formalized through the AI Autonomy Coefficient, measuring the proportion of tasks completed without mandatory human intervention. We further propose the AFHE Deployment Algorithm, an algorithmic gate that enforces a minimum autonomy threshold during offline evaluation and shadow deployment. Our results show that the AI Autonomy Coefficient effectively identifies HISOAI systems with an autonomy level of 0.38, while systems governed by the AFHE framework achieve an autonomy level of 0.85. We conclude that AFHE provides a metric-driven approach for ensuring verifiable autonomy, transparency, and sustainable operational integrity in modern AI systems.

Artificial Intelligence (AI) models increasingly drive high-stakes consumer interactions, yet their decision logic often remains opaque. Prevailing explainable AI techniques rely on post hoc numerical feature attributions, which fail to provide coherent narratives behind model decisions. Large language models (LLMs) present an opportunity to generate natural-language explanations, but three design challenges remain unresolved: explanations must be both decision-correct and faithful to the factors that drive the prediction; they should be able to serve multiple audiences without shifting the underlying decision rule; and they should be trained in a label-efficient way that does not depend on large corpora of human-scored explanations. To address these challenges, we introduce LEXMA (LLM-based EXplanations for Multi-Audience decisions), a reinforcement-learning-based fine-tuning framework that produces narrative-driven, audience-appropriate explanations. LEXMA combines reflection-augmented supervised fine-tuning with two stages of Group Relative Policy Optimization (GRPO). Specifically, it fine-tunes two separate parameter sets to improve decision correctness and satisfy stylistic requirements for different audiences, using reward signals that do not rely on human-annotated explanations. We instantiate LEXMA in the context of mortgage approval decisions. Results demonstrate that LEXMA yields significant improvements in predictive performance compared with other LLM baselines. Moreover, human evaluations show that expert-facing explanations generated by our approach are more risk-focused, and consumer-facing explanations are clearer, more actionable, and more polite. Our study contributes a cost-efficient, systematic LLM fine-tuning approach to enhance explanation quality for business decisions, offering strong potential for scalable deployment of transparent AI systems.

Uganda's rapid digital transformation, supported by national strategies such as Vision 2040 and the Digital Transformation Roadmap, has expanded reliance on networked services while simultaneously increasing exposure to sophisticated cyber threats. In resource-constrained settings, commonly deployed rule-based intrusion detection systems lack the adaptability and ethical safeguards needed to address evolving attack patterns, leading to undetected breaches and excessive blocking of legitimate traffic. This study proposes an Agentic Artificial Intelligence (AAI) framework that integrates reinforcement learning, an explicit ethical governance layer, and human oversight to deliver adaptive and trustworthy cybersecurity. A CPU-optimized simulation environment was developed using a five-node network topology that mirrors key elements of Uganda's critical digital infrastructure and generates both benign and malicious traffic, including phishing, ransomware, and distributed denial-of-service attacks. A Q-learning agent, operating within clearly defined ethical constraints and subject to human auditability, was trained and evaluated against a traditional rule-based baseline. The AAI framework achieved a 100 percent detection rate, zero false positives, and full ethical compliance, compared with 70 percent detection and 15 percent false positives for the baseline system. These results demonstrate that agentic, ethically governed reinforcement learning can substantially improve cybersecurity effectiveness and fairness in CPU-only, resource-constrained environments, offering a practical pathway for operationalizing responsible AI in Uganda's national cybersecurity strategy.

We introduce an open, machine-readable corpus of Greek government decisions sourced from the national transparency platform Diavgeia. The resource comprises 1 million decisions, featuring and high-quality raw text extracted from PDFs. It is released with raw extracted text in Markdown format, alongside a fully reproducible extraction pipeline. Beyond the core dataset, we conduct qualitative analyses to explore boilerplate patterns and design a retrieval-augmented generation (RAG) task by formulating a set of representative questions, creating high-quality answers, and evaluating a baseline RAG system on its ability to retrieve and reason over public decisions. This evaluation demonstrates the potential of large-scale public-sector corpora to support advanced information access and transparency through structured retrieval and reasoning over governmental documents, and highlights how such a RAG pipeline could simulate a chat-based assistant capable of interactively answering questions about public decisions. Due to its scale, quality, and domain coverage, the corpus can also serve as high-value pre-training or fine-tuning material for new Language Models (LMs) and Large Language Models (LLMs) respectively, including specialized models for legal and governmental domains, and as a foundation for novel approaches in domain adaptation, knowledge-grounded generation, and explainable AI. Finally, we discuss limitations, outline future directions, and make both the data and the code accessible.

This chapter discusses the ethics of generative AI. It provides a technical primer to show how generative AI affords experiencing technology as if it were human, and this affordance provides a fruitful focus for the philosophical ethics of generative AI. It then shows how generative AI can both aggravate and alleviate familiar ethical concerns in AI ethics, including responsibility, privacy, bias and fairness, and forms of alienation and exploitation. Finally, the chapter examines ethical questions that arise specifically from generative AI's mimetic generativity, such as debates about authorship and credit, the emergence of as-if social relationships with machines, and new forms of influence, persuasion, and manipulation.

Objective: To develop the AI Product Passport, a standards-based framework improving transparency, traceability, and compliance in healthcare AI via lifecycle-based documentation. Materials and Methods: The AI Product Passport was developed within the AI4HF project, focusing on heart failure AI tools. We analyzed regulatory frameworks (EU AI Act, FDA guidelines) and existing standards to design a relational data model capturing metadata across AI lifecycle phases: study definition, dataset preparation, model generation/evaluation, deployment/monitoring, and passport generation. MLOps/ModelOps concepts were integrated for operational relevance. Co-creation involved feedback from AI4HF consortium and a Lisbon workshop with 21 diverse stakeholders, evaluated via Mentimeter polls. The open-source platform was implemented with Python libraries for automated provenance tracking. Results: The AI Product Passport was designed based on existing standards and methods with well-defined lifecycle management and role-based access. Its implementation is a web-based platform with a relational data model supporting auditable documentation. It generates machine- and human-readable reports, customizable for stakeholders. It aligns with FUTURE-AI principles (Fairness, Universality, Traceability, Usability, Robustness, Explainability), ensuring fairness, traceability, and usability. Exported passports detail model purpose, data provenance, performance, and deployment context. GitHub-hosted backend/frontend codebases enhance accessibility. Discussion and Conclusion: The AI Product Passport addresses transparency gaps in healthcare AI, meeting regulatory and ethical demands. Its open-source nature and alignment with standards foster trust and adaptability. Future enhancements include FAIR data principles and FHIR integration for improved interoperability, promoting responsible AI deployment.

Vision-Language Models (VLMs) are essential for embodied AI and safety-critical applications, such as robotics and autonomous systems. However, existing benchmarks primarily focus on static or curated visual inputs, neglecting the challenges posed by adversarial conditions, value misalignment, and error propagation in continuous deployment. Current benchmarks either overlook the impact of real-world perturbations, or fail to account for the cumulative effect of inconsistent reasoning over time. To address these gaps, we introduce the Degraded Image Quality Leading to Hallucinations (DIQ-H) benchmark, the first to evaluate VLMs under adversarial visual conditions in continuous sequences. DIQ-H simulates real-world stressors including motion blur, sensor noise, and compression artifacts, and measures how these corruptions lead to persistent errors and misaligned outputs across time. The benchmark explicitly models error propagation and its long-term value consistency. To enhance scalability and reduce costs for safety-critical evaluation, we propose the Value-Guided Iterative Refinement (VIR) framework, which automates the generation of high-quality, ethically aligned ground truth annotations. VGIR leverages lightweight VLMs to detect and refine value misalignment, improving accuracy from 72.2% to 83.3%, representing a 15.3% relative improvement. The DIQ-H benchmark and VGIR framework provide a robust platform for embodied AI safety assessment, revealing vulnerabilities in error recovery, ethical consistency, and temporal value alignment.