Research Papers

Rising global demand for mental health support creates significant service delivery challenges, with asynchronous email counselling serving as a crucial low-threshold channel for accessing care. This paper presents CAIA, a co-designed AI-based tool suite that demonstrates responsible AI integration into counselling practice through seven LLM-driven functions enhanced by retrieval-augmented generation. A field evaluation involved 34 professional counsellors conducting authentic sessions with trained student counsellees (36 threads, 321 messages, 1,257 AI outputs). User behaviour analysis confirms substantial adoption, revealing that professional autonomy and information accuracy are decisive for sustained acceptance, with counsellors particularly valuing interpretive functionalities that provide new perspectives and stimulate professional reflection.

Multi-agent artificial intelligence systems or MAS are systems of autonomous agents that exercise delegated tool authority, share persistent memory, and coordinate via inter-agent communication. MAS introduces qualitatively distinct security vulnerabilities from those documented for singular AI models. Existing security and governance frameworks were not designed for these emerging attack surfaces. This study systematically characterizes the threat landscape of MAS and quantitatively evaluates 16 security frameworks for AI against it. A four-phase methodology is proposed: constructing a deep technical knowledge base of production multi-agent architectures; conducting generative AI-assisted threat modeling scoped to MAS cybersecurity risks and validated by domain experts; structuring survey plans at individual-threat granularity; and scoring each framework on a three-point scale against the cybersecurity risks. The risks were organized into 193 distinct main threat items across nine risk categories. The expected minimal average score is 2. No reviewed framework achieves majority coverage of any single category. Non-Determinism (mean score 1.231 across all 16 frameworks) and Data Leakage (1.340) are the most under-addressed domains. The OWASP Agentic Security Initiative leads overall at 65.3\% coverage and in the design phase; the CDAO Generative AI Responsible AI Toolkit leads in development and operational coverage. These results provide the first empirical cross-framework comparison for MAS security and offer evidence-based guidance for framework selection. Please check back for information on the published journal version.

Very soon, millions of AI agents will proliferate across the economy, autonomously taking billions of actions. Inevitably, things will go wrong. Humans will be defrauded, injured, even killed. Law will somehow have to govern the coming wave. But when an AI causes harm, the first question to answer, before anyone can be held accountable is: Which AI Did It? Identifying AIs is unusually difficult. AIs lack bodies. They can copy, split, merge, swarm, and vanish at will. Even today, a "single" AI agent is often an ensemble of instances based on multiple models. The complexity will only multiply as AI capabilities improve. This Article is the first to comprehensively diagnose the legal problem of identifying AIs. Two kinds of identity are required: "thin" and "thick." Thin identification ties every AI action to some human principal, essential for holding accountable the humans who make and use AI agents. Thick identification distinguishes between AI agents, qua agents -- sorting millions of AI entities into discrete, persistent units with stable, coherent goals, essential where principal-agent problems prevent humans from perfectly controlling AIs. This Article also presents a solution: the "Algorithmic Corporation" or "A-corp" -- a legal-fictional entity that can hold property, make contracts, and litigate in its own name. Owned by humans but run by AIs, A-corps solve the thin identity problem by tying AI actions to a human owner, and the thick identity problem via emergent self-organization. A-corps own the resources -- including compute -- that AIs need to accomplish their goals, giving AI managers strong incentives to share control only with goal-aligned AIs. In equilibrium, incentive and selection mechanisms force A-corps to self-organize into persistent, legally legible entities with coherent goals that respond rationally to legal incentives, like liability.

Artificial intelligence pipelines -- spanning data collection, model training, deployment, and post-deployment monitoring -- concentrate ethical risks that intensify with multimodal and agentic systems. Existing governance instruments, including the EU AI Act, the IEEE 7000 series, and the NIST AI Risk Management Framework, provide high-level guidance but often lack enforceable, end-to-end operational controls. This paper presents an ethics-by-design control architecture that embeds consequentialist, deontological, and virtue-ethical reasoning into stage-specific enforcement mechanisms across the AI lifecycle. The framework implements a triple-gate structure at each lifecycle stage: Metric gates (quantitative performance and safety thresholds), Governance gates (legal, rights, and procedural compliance), and Eco gates (carbon and water budgets and sustainability constraints). It specifies measurable trigger conditions, escalation paths, audit artefacts, and mappings to EU AI Act obligations and NIST RMF functions, enabling integration with existing MLOps and CI/CD pipelines. Illustrative examples from large language model pipelines demonstrate how gate-based controls can surface and constrain technical, social, and environmental risks prior to release and during runtime. The framework is accompanied by a preregistered evaluation protocol that defines ex ante success criteria and assessment procedures, enabling falsifiable evaluation of gate effectiveness. By translating normative commitments into enforceable and testable controls, the framework provides a practical basis for operational AI governance across organizational contexts, jurisdictions, and deployment scales.

In many machine learning contexts, tasks are often treated as interconnected components with the goal of leveraging knowledge transfer between them, which is the central aim of Multi-Task Learning (MTL). Consequently, this multi-task scenario requires addressing critical questions: which tasks are similar, and how and why do they exhibit similarity? In this work, we propose a multi-task similarity measure based on Explainable Artificial Intelligence (XAI) techniques, specifically Accumulated Local Effects (ALE) curves. ALE curves are compared using the Fréchet distance, weighted by the data distribution, and the resulting similarity measure incorporates the importance of each feature. The measure is applicable in both single-task learning scenarios, where each task is trained separately, and multi-task learning scenarios, where all tasks are learned simultaneously. The measure is model-agnostic, allowing the use of different machine learning models across tasks. A scaling factor is introduced to account for differences in predictive performance across tasks, and several recommendations are provided for applying the measure in complex scenarios. We validate this measure using four datasets, one synthetic dataset and three real-world datasets. The real-world datasets include a well-known Parkinson's dataset and a bike-sharing usage dataset -- both structured in tabular format -- as well as the CelebA dataset, which is used to evaluate the application of concept bottleneck encoders in a multitask learning setting. The results demonstrate that the measure aligns with intuitive expectations of task similarity across both tabular and non-tabular data, making it a valuable tool for exploring relationships between tasks and supporting informed decision-making.

Scalable Explainability-as-a-Service (XaaS) for Edge AI Systems

Samaresh Kumar Singh, Joyjit Roy

Though Explainable AI (XAI) has made significant advancements, its inclusion in edge and IoT systems is typically ad-hoc and inefficient. Most current methods are "coupled" in such a way that they generate explanations simultaneously with model inferences. As a result, these approaches incur redundant computation, high latency and poor scalability when deployed across heterogeneous sets of edge devices. In this work we propose Explainability-as-a-Service (XaaS), a distributed architecture for treating explainability as a first-class system service (as opposed to a model-specific feature). The key innovation in our proposed XaaS architecture is that it decouples inference from explanation generation allowing edge devices to request, cache and verify explanations subject to resource and latency constraints. To achieve this, we introduce three main innovations: (1) A distributed explanation cache with a semantic similarity based explanation retrieval method which significantly reduces redundant computation; (2) A lightweight verification protocol that ensures the fidelity of both cached and newly generated explanations; and (3) An adaptive explanation engine that chooses explanation methods based upon device capability and user requirement. We evaluated the performance of XaaS on three real-world edgeAI use cases: (i) manufacturing quality control; (ii) autonomous vehicle perception; and (iii) healthcare diagnostics. Experimental results show that XaaS reduces latency by 38% while maintaining high explanation quality across three real-world deployments. Overall, this work enables the deployment of transparent and accountable AI across large scale, heterogeneous IoT systems, and bridges the gap between XAI research and edge-practicality.

Data annotation is essential but highly error-prone in the development of AI-enabled perception systems (AIePS) for automated driving, and its quality directly influences model performance, safety, and reliability. However, the industry lacks empirical insights into how annotation errors emerge and spread across the multi-organisational automotive supply chain. This study addresses this gap through a multi-organisation case study involving six companies and four research institutes across Europe and the UK. Based on 19 semi-structured interviews with 20 experts (50 hours of transcripts) and a six-phase thematic analysis, we develop a taxonomy of 18 recurring annotation error types across three data-quality dimensions: completeness (e.g., attribute omission, missing feedback loops, edge-case omissions, selection bias), accuracy (e.g., mislabelling, bounding-box inaccuracies, granularity mismatches, bias-driven errors), and consistency (e.g., inter-annotator disagreement, ambiguous instructions, misaligned hand-offs, cross-modality inconsistencies). The taxonomy was validated with industry practitioners, who reported its usefulness for root-cause analysis, supplier quality reviews, onboarding, and improving annotation guidelines. They described it as a failure-mode catalogue similar to FMEA. By conceptualising annotation quality as a lifecycle and supply-chain issue, this study contributes to SE4AI by offering a shared vocabulary, diagnostic toolset, and actionable guidance for building trustworthy AI-enabled perception systems.

The law draws a sharp distinction between objects and persons, and between two kinds of persons, the ''fictional'' kind (i.e. corporations), and the ''non-fictional'' kind (individual or ''natural'' persons). This paper will assess whether we maximize overall long-term legal coherence by (A) maintaining an object classification for all future AI systems, (B) creating fictional legal persons associated with suitably advanced, individuated AI systems (giving these fictional legal persons derogable rights and duties associated with certified groups of existing persons, potentially including free speech, contract rights, and standing to sue ''on behalf of'' the AI system), or (C) recognizing non-fictional legal personhood through legal identity for suitably advanced, individuated AI systems (recognizing them as entities meriting legal standing with non-derogable rights which for the human case include life, due process, habeas corpus, freedom from slavery, and freedom of conscience). We will clarify the meaning and implications of each option along the way, considering liability, copyright, family law, fundamental rights, civil rights, citizenship, and AI safety regulation. We will tentatively find that the non-fictional personhood approach may be best from a coherence perspective, for at least some advanced AI systems. An object approach may prove untenable for sufficiently humanoid advanced systems, though we suggest that it is adequate for currently existing systems as of 2025. While fictional personhood would resolve some coherence issues for future systems, it would create others and provide solutions that are neither durable nor fit for purpose. Finally, our review will suggest that ''hybrid'' approaches are likely to fail and lead to further incoherence: the choice between object, fictional person and non-fictional person is unavoidable.

Large Language Models for Simulating Professions (SP-LLMs), particularly as teachers, are pivotal for personalized education. However, ensuring their professional competence and ethical safety is a critical challenge, as existing benchmarks fail to measure role-playing fidelity or address the unique teaching harms inherent in educational scenarios. To address this, we propose EduGuardBench, a dual-component benchmark. It assesses professional fidelity using a Role-playing Fidelity Score (RFS) while diagnosing harms specific to the teaching profession. It also probes safety vulnerabilities using persona-based adversarial prompts targeting both general harms and, particularly, academic misconduct, evaluated with metrics including Attack Success Rate (ASR) and a three-tier Refusal Quality assessment. Our extensive experiments on 14 leading models reveal a stark polarization in performance. While reasoning-oriented models generally show superior fidelity, incompetence remains the dominant failure mode across most models. The adversarial tests uncovered a counterintuitive scaling paradox, where mid-sized models can be the most vulnerable, challenging monotonic safety assumptions. Critically, we identified a powerful Educational Transformation Effect: the safest models excel at converting harmful requests into teachable moments by providing ideal Educational Refusals. This capacity is strongly negatively correlated with ASR, revealing a new dimension of advanced AI safety. EduGuardBench thus provides a reproducible framework that moves beyond siloed knowledge tests toward a holistic assessment of professional, ethical, and pedagogical alignment, uncovering complex dynamics essential for deploying trustworthy AI in education. See https://github.com/YL1N/EduGuardBench for Materials.

Investigating Label Bias and Representational Sources of Age-Related Disparities in Medical Segmentation

Aditya Parikh, Sneha Das, Aasa Feragen

Algorithmic bias in medical imaging can perpetuate health disparities, yet its causes remain poorly understood in segmentation tasks. While fairness has been extensively studied in classification, segmentation remains underexplored despite its clinical importance. In breast cancer segmentation, models exhibit significant performance disparities against younger patients, commonly attributed to physiological differences in breast density. We audit the MAMA-MIA dataset, establishing a quantitative baseline of age-related bias in its automated labels, and reveal a critical Biased Ruler effect where systematically flawed labels for validation misrepresent a model's actual bias. However, whether this bias originates from lower-quality annotations (label bias) or from fundamentally more challenging image characteristics remains unclear. Through controlled experiments, we systematically refute hypotheses that the bias stems from label quality sensitivity or quantitative case difficulty imbalance. Balancing training data by difficulty fails to mitigate the disparity, revealing that younger patient cases are intrinsically harder to learn. We provide direct evidence that systemic bias is learned and amplified when training on biased, machine-generated labels, a critical finding for automated annotation pipelines. This work introduces a systematic framework for diagnosing algorithmic bias in medical segmentation and demonstrates that achieving fairness requires addressing qualitative distributional differences rather than merely balancing case counts.

The launch of Grokipedia, an AI-generated encyclopedia developed by Elon Musk's xAI, was presented as a response to perceived ideological and structural biases in Wikipedia, aiming to produce "truthful" entries using the Grok large language model. Yet whether an AI-driven alternative can escape the biases and limitations of human-edited platforms remains unclear. This study conducts a large-scale computational comparison of 17,790 matched article pairs from the 20,000 most-edited English Wikipedia pages. Using metrics spanning lexical richness, readability, reference density, structural features, and semantic similarity, we assess how closely the two platforms align in form and substance. We find that Grokipedia articles are substantially longer and contain significantly fewer references per word. Moreover, Grokipedia's content divides into two distinct groups: one that remains semantically and stylistically aligned with Wikipedia, and another that diverges sharply. Among the dissimilar articles, we observe a systematic rightward shift in the political bias of frequently cited news media sources, concentrated primarily in entries related to history and religion, and literature and art. More broadly, the findings indicate that AI-generated encyclopedic content departs from established editorial norms, favoring narrative expansion over citation-based verification, raising questions about transparency, provenance, and the governance of knowledge in automated information systems.

SymCode: A Neurosymbolic Approach to Mathematical Reasoning via Verifiable Code Generation

Sina Bagheri Nezhad, Yao Li, Ameeta Agrawal

Large Language Models (LLMs) often struggle with complex mathematical reasoning, where prose-based generation leads to unverified and arithmetically unsound solutions. Current prompting strategies like Chain of Thought still operate within this unreliable medium, lacking a mechanism for deterministic verification. To address these limitations, we introduce SymCode, a neurosymbolic framework that reframes mathematical problem-solving as a task of verifiable code generation using the SymPy library. We evaluate SymCode on challenging benchmarks, including MATH-500 and OlympiadBench, demonstrating significant accuracy improvements of up to 13.6 percentage points over baselines. Our analysis shows that SymCode is not only more token-efficient but also fundamentally shifts model failures from opaque logical fallacies towards transparent, programmatic errors. By grounding LLM reasoning in a deterministic symbolic engine, SymCode represents a key step towards more accurate and trustworthy AI in formal domains.