Transparency

Large language models (LLMs) exhibit strong general capabilities, but their deployment in high-stakes domains is hindered by their opacity and unpredictability. Recent work has taken meaningful steps towards addressing these issues by augmenting LLMs with post-hoc reasoning based on computational argumentation, providing faithful explanations and enabling users to contest incorrect decisions. However, this paradigm is limited to pre-defined binary choices and only supports local contestation for

Contrastive pretraining models such as CLIP and CLAP, serve as the ubiquitous perceptual backbones for modern multimodal large models, yet their reliance on web-scale data raises growing concerns about memorizing Personally Identifiable Information (PII). Auditing such models via membership inference is challenging in practice: shadow-model MIAs are computationally prohibitive for large multimodal backbones, and existing multimodal auditing methods typically require querying the target with pair

Climate-vulnerable road networks require a paradigm shift from reactive, fix-on-failure repairs to predictive, decision-ready maintenance. This paper introduces ST-ResGAT, a novel Spatio-Temporal Residual Graph Attention Network that fuses residual graph-attention encoding with GRU temporal aggregation to forecast pavement deterioration. Engineered for resource-constrained deployment, the framework translates continuous Pavement Condition Index (PCI) forecasts directly into the American Society

We introduce CRYSTAL (Clear Reasoning via Yielded Steps, Traceability, and Logic), a diagnostic benchmark with 6,372 instances that evaluates multimodal reasoning through verifiable intermediate steps. We propose two complementary metrics: Match F1, which scores step-level precision and recall via semantic similarity matching, and Ordered Match F1, which further penalizes disordered reasoning chains. References are constructed through a Delphi-inspired pipeline in which four independent MLLMs ge

Neuro-symbolic reasoning increasingly demands frameworks that unite the formal rigor of logic with the interpretability of large language models (LLMs). We introduce an end to end explainability by construction pipeline integrating the Automated Theorem Generator Delta1 based on the full triangular standard contradiction (FTSC) with LLMs. Delta1 deterministically constructs minimal unsatisfiable clause sets and complete theorems in polynomial time, ensuring both soundness and minimality by const

The rapid advancement and impressive capabilities of large language models (LLMs) have given rise to the field of prompt engineering, the practice of crafting inputs to guide LLMs toward high-quality, task-relevant outputs. A critical challenge facing the field is the lack of standardised prompt documentation and evaluation practices. Prompts can be long, complex and difficult to evaluate on subjective tasks. To address this challenge, we propose the use of prompt cards, structured summaries of

Artificial intelligence systems are increasingly embedded in high-stakes decision environments, yet many governance approaches focus primarily on policy guidance rather than operational stability mechanisms. As AI deployments scale, organizations require governance architectures capable of maintaining reliable, auditable, and accountable behavior over time. This paper introduces the AI Governance Control Stack for Operational Stability, a layered governance architecture designed to ensure tracea

Standard fairness audits of foundation models quantify that a model is biased, but not where inside the network the bias resides. We propose a mechanistic fairness audit that combines projected residual-stream decomposition, zero-shot Concept Activation Vectors, and bias-augmented TextSpan analysis to locate demographic bias at the level of individual attention heads in vision transformers. As a feasibility case study, we apply this pipeline to the CLIP ViT-L-14 encoder on 42 profession classes

The study of the attribution of input features to the output of neural network models is an active area of research. While numerous Explainable AI (XAI) techniques have been proposed to interpret these models, the systematic and automated evaluation of these methods in sequence-to-sequence (seq2seq) models is less explored. This paper introduces a new approach for evaluating explainability methods in transformer-based seq2seq models. We use teacher-derived attribution maps as a structured side s

Large language models (LLMs) are increasingly applied to financial analysis, yet their ability to audit structured financial statements under explicit accounting principles remains poorly explored. Existing benchmarks primarily evaluate question answering, numerical reasoning, or anomaly detection on synthetically corrupted data, making it unclear whether models can reliably verify or localize rule compliance on correct financial statements. We introduce FinRule-Bench, a benchmark for evaluating

This editorial addresses the critical intersection of artificial intelligence (AI) and blockchain technologies, highlighting their contrasting tendencies toward centralization and decentralization, respectively. While AI, particularly with the rise of large language models (LLMs), exhibits a strong centralizing force due to data and resource monopolization by large corporations, blockchain offers a counterbalancing mechanism through its inherent decentralization, transparency, and security. The

The rapid proliferation of large language model (LLM)-based agentic systems raises critical concerns regarding digital sovereignty, environmental sustainability, regulatory compliance, and ethical alignment. Whilst existing frameworks address individual dimensions in isolation, no unified architecture systematically integrates these imperatives into the decision-making processes of autonomous agents. This paper introduces the COMPASS (Compliance and Orchestration for Multi-dimensional Principles

Clinical diagnosis is a complex cognitive process, grounded in dynamic cue acquisition and continuous expertise accumulation. Yet most current artificial intelligence (AI) systems are misaligned with this reality, treating diagnosis as single-pass retrospective prediction while lacking auditable mechanisms for governed improvement. We developed DxEvolve, a self-evolving diagnostic agent that bridges these gaps through an interactive deep clinical research workflow. The framework autonomously req

Computer-Use Agents (CUAs) are emerging as a new paradigm in human-computer interaction, enabling autonomous execution of tasks in desktop environment by perceiving high-level natural-language instructions. As such agents become increasingly capable and are deployed across diverse desktop environments, evaluating their behavior in a scalable and reliable manner becomes a critical challenge. Existing evaluation pipelines rely on static benchmarks, rule-based success checks, or manual inspection,

As Large Vision-Language Models (LVLMs) are increasingly deployed in agent-integrated workflows and other deployment-relevant settings, their robustness against semantic visual attacks remains under-evaluated -- alignment is typically tested on explicit harmful content rather than privacy-critical multimodal scenarios. We introduce VisualLeakBench, an evaluation suite to audit LVLMs against OCR Injection and Contextual PII Leakage using 1,000 synthetically generated adversarial images with 8 PII

Software vulnerabilities often depend on cross-file data flow, build options, framework conventions, and runtime guards, so isolated function classifiers produce fragile and poorly calibrated warnings. Repository-level LLM agents can gather richer evidence, but prior variants under-specify reproducibility, verifier behavior, baseline fairness, and statistical uncertainty. We present VulnAgent-R2, a budget-aware agentic auditing framework with three additional reusable modules: counterfactual evi

The discovery and design of functional molecules remain central challenges across chemistry,biology, and materials science. While recent advances in machine learning have accelerated molecular property prediction and candidate generation, existing models tend to excel either in physical fidelity without transparent reasoning, or in flexible reasoning without guarantees of chemical validity. This imbalance limits the reliability of artificial intelligence systems in real scientific design workflo

Ensuring trustworthiness in open-world visual recognition requires models that are interpretable, fair, and robust to distribution shifts. Yet modern vision systems are increasingly deployed as proprietary black-box APIs, exposing only output probabilities and hiding architecture, parameters, gradients, and training data. This opacity prevents meaningful auditing, bias detection, and failure analysis. Existing explanation methods assume white- or gray-box access or knowledge of the training dist

Aircraft engine blade maintenance relies on inspection records shared across manufacturers, airlines, maintenance organizations, and regulators. Yet current systems are fragmented, difficult to audit, and vulnerable to tampering. This paper presents BladeChain, a blockchain-based system providing immutable traceability for blade inspections throughout the component life cycle. BladeChain is the first system to integrate multi-stakeholder endorsement, automated inspection scheduling, AI model pro

Reward modeling is essential for aligning Large Language Models(LLMs) with human preferences, yet conventional reward models suffer from poor interpretability and heavy reliance on costly expert annotations. While recent rubric-based approaches enhance evaluation transparency, they lack systematic quality control, yielding noisy and redundant criteria, failing to mitigate persistent biases (e.g., verbosity, position) in LLM evaluators, and creating a scalability-reliability trade-off. To address

Explaining out-of-distribution generalization has been a central problem in epistemology since Goodman's "grue" puzzle in 1946. Today it's a central problem in machine learning, including AI alignment. Here we propose a principled account of OOD generalization with three main ingredients. First, the world is always presented to experience not as an amorphous mass, but via distinguished features (for example, visual and auditory channels). Second, Occam's Razor favors hypotheses that are "sparse,

Autonomous agents powered by large language models introduce a class of execution-layer vulnerabilities -- prompt injection, retrieval poisoning, and uncontrolled tool invocation -- that existing guardrails fail to address systematically. In this work, we propose the Layered Governance Architecture (LGA), a four-layer framework comprising execution sandboxing (L1), intent verification (L2), zero-trust inter-agent authorization (L3), and immutable audit logging (L4). To evaluate LGA, we construct

Explainable Artificial Intelligence (XAI) seeks to enhance the transparency and accountability of machine learning systems, yet most methods follow a one-size-fits-all paradigm that neglects user differences in expertise, goals, and cognitive needs. Although Large Language Models can translate technical explanations into natural language, they introduce challenges related to faithfulness and hallucinations. To address these challenges, we present PONTE (Personalized Orchestration for Natural lan

AI-assisted software generation has increased development speed, but it has also amplified a persistent engineering problem: systems that are functionally correct may still be structurally insecure. In practice, prompt-based security review with large language models often suffers from uneven coverage, weak reproducibility, unsupported findings, and the absence of an immutable audit trail. The ESAA architecture addresses a related governance problem in agentic software engineering by separating

Large Language Models (LLMs) are increasingly being deployed in multilingual, multicultural settings, yet their reliance on predominantly English-centric training data risks misalignment with the diverse cultural values of different societies. In this paper, we present a comprehensive, multilingual audit of the cultural alignment of contemporary LLMs including GPT-4o-Mini, Gemini-2.5-Flash, Llama 3.2, Mistral and Gemma 3 across India, East Asia and Southeast Asia. Our study specifically focuses

While explainable AI (XAI) is often heralded as a means to enhance transparency and trustworthiness in closed-loop neurotechnology for psychiatric and neurological conditions, its real-world prevalence remains low. Moreover, empirical evidence suggests that the type of explanations provided by current XAI methods often fails to align with clinicians' end-user needs. In this viewpoint, we argue that clinically meaningful explainability (CME) is essential for AI-enabled closed-loop medical neurote

Adolescents spend an increasing amount of their time in digital environments where their still-developing cognitive capacities leave them unable to recognize or resist commercial persuasion. Article 28(2) of the DSA responds to this vulnerability by prohibiting profiling-based advertising to minors. However, the regulation's narrow definition of "advertisement" excludes current advertising practices including influencer paid partnerships and brand promotional content that serve functionally equi

The smart home is a key application domain within the Society 5.0 vision for a human-centered society. As smart home ecosystems expand with heterogeneous IoT protocols, diverse devices, and evolving threats, autonomous systems must manage comfort, security, energy, and safety for residents. Such autonomous decision-making requires a trust anchor, making blockchain a preferred foundation for transparent and accountable smart home governance. However, realizing this vision requires blockchain-gove

This article presents a Delphi consensus developed by a panel of editors-in-chief of anaesthesiology and pain medicine journals to guide the responsible use of large language models (LLMs) in academic publishing. LLMs offer potential benefits for scientific writing, including language editing, summarisation, translation, information organisation, and support for non-native English speakers, but their misuse raises concerns about accuracy, transparency, confidentiality, and research integrity. Th

Abstract Clinical prediction models are often created using large routinely collected datasets. It is essential that prediction models are developed with appropriate data and methods and transparently reported to ensure that decisions are based on reliable predictions. Kaggle is a popular competition and data repository website where users learn and apply analysis skills on a range of datasets. We identified two large, publicly available Kaggle datasets, on stroke and diabetes, that lack clear d

BACKGROUND: The integration of artificial intelligence in healthcare has transformed clinical practice and research methodologies. However, concerns regarding algorithmic accountability, interpretability, and safety have necessitated human oversight in AI systems. Human in the loop artificial intelligence represents a collaborative paradigm where human expertise and machine intelligence converge to enhance decision making while maintaining ethical standards and clinical safety. AIM: This review

Background: Corporate governance is an essential framework for enhancing performance efficiency, accountability, and ethical behavior within corporations. Emerging technologies, particularly artificial intelligence (AI), have infiltrated traditional corporate governance models, management practices, and decision-making processes due to their tremendous capabilities. However, implementation poses a significant challenge due to unresolved legal and ethical issues concerning the anthropocentric mod

This paper offers a conceptual analysis of the transformative role of Artificial Intelligence (AI) in urban governance, focusing on how AI can reshape the relationship between bureaucratic discretion and accountability. Drawing on public administration theory and algorithmic governance research, the study argues that AI does not simply restrict or enhance discretion but redistributes it across institutional levels, professional roles, and citizen interactions. While primarily conceptual, this pa

In recent years, much of the research on clustering algorithms has primarily focused on enhancing their accuracy and efficiency, frequently at the expense of interpretability. However, as these methods are increasingly being applied in high-stakes domains such as healthcare, finance, and autonomous systems, the need of transparent and interpretable clustering outcomes has become a critical concern. This is not only necessary for gaining user trust but also for satisfying the growing ethical and

Generative Artificial Intelligence (GenAI) models produce increasingly sophisticated outputs, yet their underlying mechanisms remain opaque. To clarify how explainability is conceptualized and implemented in GenAI research, this two-stage review systematically examined 261 articles retrieved from six major databases. After removing duplicates and applying predefined inclusion criteria, 63 articles were retained for full analysis. In the first stage, an umbrella review synthesized insights from 1

Abstract Conventional electromagnetic cloaking paradigms predominantly necessitate the encasing of static objects within predefined topological enclosures, fundamentally restricting invisibility to fixed, closed geometries. Realizing dynamic, adaptive concealment for arbitrary moving targets within an open, boundary-free aperture remains a formidable challenge. Here, we report a meta-reinforcement-learning metasurface (Meta 2 Surface) that enables the first experimental demonstration of a "trans

The opaque nature of black-box deep learning (DL) models poses significant challenges for intrusion detection systems (IDSs) in Internet of Things (IoT) networks, where transparency, trust, and operational reliability are critical. Although explainable artificial intelligence (XAI) has been increasingly adopted to enhance interpretability, its impact on detection performance and computational efficiency in resource-constrained IoT environments remains insufficiently understood. This systematic r

This study introduces the Islamic Ḥiwār Framework (IHF), a multi-layered, KPI-based architecture developed to operationalize intra-faith dialogue within Islamic contexts by translating theological, ethical, and institutional principles into measurable performance indicators. Drawing from Islamic epistemology, dialogical ethics, and governance structures, the IHF addresses the need for a strategic, accountable, and scalable model for religious rapprochement. A mixed-methods approach was employed,

Advances in artificial intelligence (AI) have made it easier to create highly realistic deepfake videos, which can appear to show someone doing or saying something they did not do or say. Deepfakes may present a threat to individuals and society: for example, deepfakes can be used to influence elections by discrediting political opponents. Psychological research shows that people's ability to detect deepfake videos varies considerably, making us potentially vulnerable to the influence of a video

Background: Theintegration of artificial intelligence (AI) into clinical decision support systems (CDSSs) has significantly enhanced diagnostic precision, risk stratification, and treatment planning. AI models remain a barrier to clinical adoption, emphasizing the critical role of explainable AI (XAI). Methods: This systematic meta-analysis synthesizes findings from 62 peer-reviewed studies published between 2018 and 2025, examining the use of XAI methods within CDSSs across various clinical dom