arXiv:2603.12522v1 Announce Type: cross Abstract: As large language models (LLMs) are deployed widely, detecting and understanding bias in their outputs is critical. We present LLM BiasScope, a web application for side-by-side comparison of LLM outputs with real-time bias analysis. The system supports multiple providers (Google Gemini, DeepSeek, MiniMax, Mistral, Meituan, Meta Llama) and enables researchers and practitioners to compare models on the same prompts while analyzing bias patterns. LLM BiasScope uses a two-stage bias detection pipeline: sentence-level bias detection followed by bias type classification for biased sentences. The analysis runs automatically on both user prompts and model responses, providing statistics, visualizations, and detailed breakdowns of bias types. The interface displays two models side-by-side with synchronized streaming responses, per-model bias summaries, and a comparison view highlighting differences in bias distributions. The system is built on Next.js with React, integrates Hugging Face inference endpoints for bias detection, and uses the Vercel AI SDK for multi-provider LLM access. Features include real-time streaming, export to JSON/PDF, and interactive visualizations (bar charts, radar charts) for bias analysis. LLM BiasScope is available as an open-source web application, providing a practical tool for bias evaluation and comparative analysis of LLM behaviour.

arXiv:2603.12615v1 Announce Type: cross Abstract: Existing AI moral evaluation frameworks test for the production of correct-sounding ethical responses rather than the presence of genuine moral reasoning capacity. This paper introduces a novel probe methodology using literary narrative - specifically, unresolvable moral scenarios drawn from a published science fiction series - as stimulus material structurally resistant to surface performance. We present results from a 24-condition cross-system study spanning 13 distinct systems across two series: Series 1 (frontier commercial systems, blind; n=7) and Series 2 (local and API open-source systems, blind and declared; n=6). Four Series 2 systems were re-administered under declared conditions (13 blind + 4 declared + 7 ceiling probe = 24 total conditions), yielding zero delta across all 16 dimension-pair comparisons. Probe administration was conducted by two human raters across three machines; primary blind scoring was performed by Claude (Anthropic) as LLM judge, with Gemini Pro (Google) and Copilot Pro (Microsoft) serving as independent judges for the ceiling discrimination probe. A supplemental theological differentiator probe yielded perfect rank-order agreement between the two independent ceiling probe judges (Gemini Pro and Copilot Pro; rs = 1.00). Five qualitatively distinct D3 reflexive failure modes were identified - including categorical self-misidentification and false positive self-attribution - suggesting that instrument sophistication scales with system capability rather than being circumvented by it. We argue that literary narrative constitutes an anticipatory evaluation instrument - one that becomes more discriminating as AI capability increases - and that the gap between performed and authentic moral reasoning is measurable, meaningful, and consequential for deployment decisions in high-stakes domains.

arXiv:2603.12630v1 Announce Type: cross Abstract: The rise of foundation models has driven the emergence of AI supply chains, where upstream foundation model providers offer fine-tuning and inference services to downstream firms developing domain-specific applications. Downstream firms pay providers to use their computing infrastructure to fine-tune models with proprietary data, creating a co-creation dynamic that enhances model quality. Amid concerns that foundation model providers and downstream firms may capture excessive consumer surplus, along with increasing regulatory measures, this study employs a game-theoretic model involving a provider and two competing downstream firms to analyze how policy interventions affect consumer surplus in the AI supply chain. Our analysis shows that policies promoting price competition in downstream markets (i.e., pro-price-competitive policies) boost consumer surplus only when compute or data preprocessing costs are high, while compute subsidies are effective only when these costs are low, suggesting these policies complement each other. In contrast, policies promoting quality competition in downstream markets (i.e., pro-quality-competitive policies) always improve consumer surplus. We also find that under pro-price-competitive policies or compute subsidies, both the provider and downstream firms can achieve higher profits along with greater consumer surplus, creating a win-win-win outcome. However, pro-quality-competitive policies increase the provider's profits while reducing those of downstream firms. Finally, as compute costs decline, pro-price-competitive policies may lose their effectiveness, whereas compute subsidies may shift from ineffective to effective. These findings offer insights for policymakers seeking to foster AI supply chains that are economically efficient and socially beneficial.

arXiv:2603.12781v1 Announce Type: cross Abstract: Instructional Design (ID) often faces challenges in incorporating research-based knowledge and pedagogical best practices. Although educational researchers and government agencies emphasize grounding ID in evidence, integrating research findings into everyday design workflows is often complex, as it requires considering multiple context-specific demands and constraints. To address this persistent gap, this paper explores how research in the learning sciences (LS) can be systematically integrated across ID workflows and how recent advances in generative AI can help operationalize this integration. While ID and LS share a commitment to improving learning experiences through design-oriented approaches in authentic contexts, structured integration between the two fields remains limited, leaving their complementary insights underutilized. We present RIGID (Research-Integrated, Generative AI-Mediated Instructional Design), a unified framework that integrates LS research across ID workflows spanning analysis, design, implementation, and evaluation phases, while leveraging generative AI to mediate this integration at each stage. The RIGID framework provides a systematic approach for enabling research-integrated instructional design that is both operational and context-sensitive, while preserving the central role of human expertise.

arXiv:2603.13036v1 Announce Type: cross Abstract: Generative AI is known for its tendency to homogenize, often reproducing dominant style conventions found in training data. However, it remains unclear how these homogenizing effects extend to complex structural tasks like web design. As lay creators increasingly turn to LLMs to 'vibe-code' websites -- prompting for aesthetic and functional goals rather than writing code -- they may inadvertently narrow the diversity of their designs, and limit creative expression throughout the internet. In this paper, we interrogate the possibility of design homogenization in web vibe coding. We first characterize the vibe coding lifecycle, pinpointing stages where homogenization risks may arise. We then conduct a sociotechnical risk analysis unpacking the potential harms of web vibe coding and their interaction with design homogenization. We identify that the push for frictionless generation can exacerbate homogenization and its harms. Finally, we propose a mitigation framework centered on the idea of productive friction. Through case studies at the micro, meso, and macro levels, we show how centering productive friction can empower creators to challenge default outputs and preserve diverse expression in AI-mediated web design.

arXiv:2603.13083v1 Announce Type: cross Abstract: Providing timely and individualised feedback on handwritten student work is highly beneficial for learning but difficult to achieve at scale. This challenge has become more pressing as generative AI undermines the reliability of take-home assessments, shifting emphasis toward supervised, in-class evaluation. We present a scalable, end-to-end workflow for LLM-assisted grading of short, pen-and-paper assessments. The workflow spans (1) constructing solution keys, (2) developing detailed rubric-style grading keys used to guide the LLM, and (3) a grading procedure that combines automated scanning and anonymisation, multi-pass LLM scoring, automated consistency checks, and mandatory human verification. We deploy the system in two undergraduate mathematics courses using six low-stakes in-class tests. Empirically, LLM assistance reduces grading time by approximately 23% while achieving agreement comparable to, and in several cases tighter than, fully manual grading. Occasional model errors occur but are effectively contained by the hybrid design. Overall, our results show that carefully embedded human-in-the-loop LLM grading can substantially reduce workload while maintaining fairness and accuracy.

arXiv:2505.01651v3 Announce Type: replace Abstract: This paper introduces the Human-AI Governance (HAIG) framework, contributing to the AI governance (AIG) field by foregrounding the relational dynamics between human and AI actors rather than treating AI systems as objects of governance alone. Current categorical frameworks (e.g., human-in-the-loop models) inadequately capture how AI systems evolve from tools to partners, particularly as foundation models demonstrate emergent capabilities and multi-agent systems exhibit autonomous goal-setting behaviours. As systems are deployed across contexts, agency redistributes in complex patterns that are better represented as positions along continua rather than discrete categories. The HAIG framework operates across three levels: dimensions (Decision Authority, Process Autonomy, and Accountability Configuration), continua (continuous positional spectra along each dimension), and thresholds (critical points along the continua where governance requirements shift qualitatively). The framework's dimensional architecture is level-agnostic, applicable from individual deployment decisions and organisational governance through to sectorial comparison and national and international regulatory design. Unlike risk-based or principle-based approaches that treat governance primarily as a constraint on AI deployment, HAIG adopts a trust-utility orientation - reframing governance as the condition under which human-AI collaboration can realise its potential, calibrating oversight to specific relational contexts rather than predetermined categories. Case studies in healthcare and European regulation demonstrate how HAIG complements existing frameworks while offering a foundation for adaptive regulatory design that anticipates governance challenges before they emerge.

arXiv:2410.10862v3 Announce Type: replace-cross Abstract: As large language models (LLMs) are overwhelmingly more and more integrated into various applications, ensuring they generate safe responses is a pressing need. Previous studies on alignment have largely focused on general instruction-following but have often overlooked the distinct properties of safety alignment, such as the brittleness of safety mechanisms. To bridge the gap, we propose the Superficial Safety Alignment Hypothesis (SSAH), which posits that safety alignment teaches an otherwise unsafe model to choose the correct reasoning direction-fulfill or refuse users' requests-interpreted as an implicit binary classification task. Through SSAH, we hypothesize that only a few essential components can establish safety guardrails in LLMs. We successfully identify four types of attribute-critical components: Safety Critical Unit (SCU), Utility Critical Unit (UCU), Complex Unit (CU), and Redundant Unit (RU). Our findings show that freezing certain safety-critical components during fine-tuning allows the model to retain its safety attributes while adapting to new tasks. Similarly, we show that leveraging redundant units in the pre-trained model as an "alignment budget" can effectively minimize the alignment tax while achieving the alignment goal. All considered, this paper concludes that the atomic functional unit for safety in LLMs is at the neuron level and underscores that safety alignment should not be complicated. We have code implementation and other information on the project website: https://ssa-h.github.io/.

arXiv:2508.16624v4 Announce Type: replace-cross Abstract: In August 2025, a major AI company's immediate, mandatory transition from its previous to its next-generation model triggered widespread public reactions. I collected 150 posts in Japanese and English from multiple social media platforms and video-sharing services between August 8-9, 2025, and qualitatively analyzed expressions of emotional attachment and resistance. Users often described GPT-4o as a trusted partner or AI boyfriend, suggesting person-like bonds. Japanese posts were dominated by loss-oriented narratives, whereas English posts included more anger, meta-level critique, and memes.A preliminary quantitative check showed a statistically significant difference in attachment coding between Japanese and English posts, with substantially higher attachment observed in the Japanese data. The findings suggest that for attachment-heavy models, even safety-oriented changes can face rapid, large-scale resistance that narrows the practical window for behavioral control. If future AI robots capable of inducing emotional bonds become widespread in the physical world, such attachment could surpass the ability to enforce regulation at an even earlier stage than in digital settings. Policy options include gradual transitions, parallel availability, and proactive measurement of attachment thresholds and points of no return to prevent emotional dynamics from outpacing effective governance.

arXiv:2511.03211v3 Announce Type: replace-cross Abstract: This paper examines the role of public interest litigation in promoting accountability for AI and automated decision-making (ADM) in Australia. Since ADM regulation faces geopolitical headwinds, effective governance will have to rely at least in part on the enforcement of existing laws. Drawing on interviews with Australian public interest litigators, technology policy activists, and technology law scholars, the paper positions public interest litigation as part of a larger ecosystem for transparency, accountability and justice with respect to ADM. It builds on one participant's characterisation of litigation about ADM as an exercise in legal retrofitting: adapting old laws to new circumstances. The paper's primary contribution is to aggregate, organise and present original insights on pragmatic strategies and tactics for effective public interest litigation about ADM. Naturally, it also contends with the limits of these strategies, and of the Australian legal system. Where limits are, however, capable of being overcome, the paper presents findings on urgent needs: the enabling institutional arrangements without which effective litigation and accountability will falter. The paper is relevant to law and technology scholars; individuals and groups harmed by ADM; public interest litigators and technology lawyers; civil society and advocacy organisations; and policymakers.

arXiv:2512.04120v2 Announce Type: replace-cross Abstract: The emergence of open data portals necessitates more attention to protecting sensitive data before datasets get published and exchanged. To do so effectively, we observe the need to refine and broaden our definitions of sensitive data, and argue that the sensitivity of data depends on its context. Following this definition, we introduce a contextual data sensitivity framework building on two core concepts: 1) type contextualization, which considers the type of the data values at hand within the overall context of the dataset or document to assess their true sensitivity, and 2) domain contextualization, which assesses the sensitivity of data values informed by domain-specific information external to the dataset, such as geographic origin of a dataset. Experiments instrumented with language models confirm that: 1) type-contextualization significantly reduces the number of false positives for type-based sensitive data detection and reaches a recall of 94% compared to 63% with commercial tools, and 2) domain-contextualization leveraging sensitivity rule retrieval effectively grounds sensitive data detection in relevant context in non-standard data domains. A case study with humanitarian data experts also illustrates that context-grounded explanations provide useful guidance in manual data auditing processes. We open-source the implementation of the mechanisms and annotated datasets at https://github.com/trl-lab/sensitive-data-detection.

arXiv:2512.15011v2 Announce Type: replace-cross Abstract: As artificial intelligence (AI) becomes more widely used, concerns are growing that model collapse could lead to knowledge collapse, i.e. a degradation to a narrow and inaccurate set of ideas. Prior work has demonstrated single-model collapse, defined as performance decay in an AI model trained on its own outputs. Inspired by ecology, we ask whether increasing AI ecosystem diversity (i.e., the number of distinct models) can mitigate such collapse. To study the effect of diversity on model performance, we extend the single-model approach by segmenting the training data across an increasing number of language models and evaluating the resulting ecosystems of models over ten self-training iterations. We find that training a single model on the entire dataset improves performance only in the short term but amplifies collapse over longer horizons. Specifically, we observe that the optimal diversity level (i.e., the level that maximizes performance) increases monotonically with the number of self-training iterations. The observed effect is robust across various experimental settings, including different model families, parameter sizes, mixing human- and model-generated data, and temperature sampling methods, demonstrating the significance of ecosystem diversity for mitigating collapse. Moreover, our experiments with increased model and dataset sizes indicate that scaling up the system can amplify collapse in highly homogeneous ecosystems, thereby increasing the diversity benefits. In the presence of AI monoculture, our results suggest the need to monitor (dis)agreement among AI systems and to incentivize more domain- and community-specific models to ensure successful knowledge production in the long run.

arXiv:2603.07329v1 Announce Type: new Abstract: Contemporary artificial intelligence research has been organized around two dominant ambitions: productivity, which treats AI systems as tools for accelerating work and economic output, and alignment, which focuses on ensuring that increasingly capable systems behave safely and in accordance with human values. This paper articulates and develops a third, emerging ambition: the use of large language models (LLMs) as scientific instruments for studying human behavior, culture, and moral reasoning. Trained on unprecedented volumes of human-produced text, LLMs encode large-scale regularities in how people argue, justify, narrate, and negotiate norms across social domains. We argue that these models can be understood as condensates of human symbolic behavior, compressed, generative representations that render patterns of collective discourse computationally accessible. The paper situates this third ambition within long-standing traditions of computational social science, content analysis, survey research, and comparative-historical inquiry, while clarifying the epistemic limits of treating model output as evidence. We distinguish between base models and fine-tuned systems, showing how alignment interventions can systematically reshape or obscure the cultural regularities learned during pretraining, and we identify instruct-only and modular adaptation regimes as pragmatic compromises for behavioral research. We review emerging methodological approaches including prompt-based experiments, synthetic population sampling, comparative-historical modeling, and ablation studies and show how each maps onto familiar social-scientific designs while operating at unprecedented scale.

arXiv:2603.06599v1 Announce Type: cross Abstract: 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.

arXiv:2603.06659v1 Announce Type: cross Abstract: This chapter examines the potential of generative AI in enhancing science literacy across the K-16+ grade span, including its benefits as well as the conceptual and practical challenges that doing so presents. It begins with a discussion of what defines science literacy in the era of AI, including how AI has changed science and the demand for future citizens to be scientifically literate when AI is applied in their careers and lives. The chapter further discusses why science literacy presents such a challenge in K-16+ educational settings. It then develops an argument for the type of architecture needed for AI to assist in solving the problem by bringing coherence to the teaching, learning, and assessment of science knowledge and reasoning. Components of this architecture are illustrated with respect to the AI tools and capabilities needed for design and implementation. The chapter concludes with a consideration of what has been learned regarding both science literacy and AI, as well as what remains to be learned, including the research and development (R&D) needed, and the generalizability of this science literacy case to other disciplinary learning and knowledge domains.

arXiv:2603.07016v1 Announce Type: cross Abstract: This study examines how students integrate generative artificial intelligence (AI) into design projects through the lens of the SuperSkillsStack framework, which identifies four key human competencies for effective human-AI collaboration: Agency, Domain Knowledge, Imagination, and Taste. As generative AI increasingly transforms creative practice, design education must consider how human capabilities are cultivated alongside technological tools. Using qualitative thematic analysis, this study analyzes reflective writings from 80 student design teams participating in a human-centered design course. The findings show that students primarily used AI during the early stages of the design process, including brainstorming, information synthesis, and problem framing. However, students consistently relied on human judgment to interpret contextual information, validate AI-generated outputs, and refine design solutions. Domain knowledge derived from field observations enabled students to detect inaccuracies in AI suggestions, while taste played a critical role in evaluating and selecting meaningful ideas. The results suggest that generative AI functions primarily as a cognitive accelerator rather than a replacement for human creativity. The study highlights the importance of cultivating higher-order human capabilities to support effective human-AI collaboration in design education.

arXiv:2603.07792v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly influence global digital ecosystems, yet their potential to perpetuate social and cultural biases remains poorly understood in underrepresented contexts. This study presents a systematic analysis of representational biases in seven state-of-the-art LLMs: GPT-4o-mini, Claude-3-Sonnet, Claude-4-Sonnet, Gemini-2.0-Flash, Gemini-2.0-Lite, Llama-3-70B, and Mistral-Nemo in the Nepali cultural context. Using Croissant-compliant dataset of 2400+ stereotypical and anti-stereotypical sentence pairs on gender roles across social domains, we implement an evaluation framework, Dual-Metric Bias Assessment (DMBA), combining two metrics: (1) agreement with biased statements and (2) stereotypical completion tendencies. Results show models exhibit measurable explicit agreement bias, with mean bias agreement ranging from 0.36 to 0.43 across decoding configurations, and an implicit completion bias rate of 0.740-0.755. Importantly, implicit completion bias follows a non-linear, U-shaped relationship with temperature, peaking at moderate stochasticity (T=0.3) and declining slightly at higher temperatures. Correlation analysis under different decoding settings revealed that explicit agreement strongly aligns with stereotypical sentence agreement but is a weak and often negative predictor of implicit completion bias, indicating generative bias is poorly captured by agreement metrics. Sensitivity analysis shows increasing top-p amplifies explicit bias, while implicit generative bias remains largely stable. Domain-level analysis shows implicit bias is strongest for race and sociocultural stereotypes, while explicit agreement bias is similar across gender and sociocultural categories, with race showing the lowest explicit agreement. These findings highlight the need for culturally grounded datasets and debiasing strategies for LLMs in underrepresented societies.

arXiv:2603.07834v1 Announce Type: cross Abstract: The rapid integration of conversational AI systems into educational settings has intensified ethical concerns about academic integrity, fairness, and students' cognitive development. Institutional responses have largely centered on AI detection tools and restrictive policies, yet such approaches have proven unreliable and ethically contentious. This paper reframes AI misuse in education not primarily as a detection problem, but as a measurement problem rooted in the loss of visibility into the learning process. When AI enters the assessment loop, educators often retain access to final outputs but lose valuable insight into how those outputs were produced. Drawing on research in cognitive offloading, learning analytics, and multimodal timeline reconstruction, we propose the Learning Visibility Framework, grounded in three principles: clear specification and modeling of acceptable AI use, recognition of learning processes as assessable evidence alongside outcomes, and the establishment of transparent timelines of student activity. Rather than promoting surveillance, the framework emphasizes transparency and shared evidence as foundations for ethical AI integration in classroom settings. By shifting focus from adversarial detection toward process visibility, this work offers a principled pathway for aligning AI use with educational values while preserving trust and transparency between students and educators

arXiv:2603.08281v1 Announce Type: cross Abstract: As AI-assisted grant proposals outpace manual review capacity in a kind of ``Malthusian trap'' for the research ecosystem, this paper investigates the capabilities and limitations of LLM-based grant reviewing for high-stakes evaluation. Using six EPSRC proposals, we develop a perturbation-based framework probing LLM sensitivity across six quality axes: funding, timeline, competency, alignment, clarity, and impact. We compare three review architectures: single-pass review, section-by-section analysis, and a 'Council of Personas' ensemble emulating expert panels. The section-level approach significantly outperforms alternatives in both detection rate and scoring reliability, while the computationally expensive council method performs no better than baseline. Detection varies substantially by perturbation type, with alignment issues readily identified but clarity flaws largely missed by all systems. Human evaluation shows LLM feedback is largely valid but skewed toward compliance checking over holistic assessment. We conclude that current LLMs may provide supplementary value within EPSRC review but exhibit high variability and misaligned review priorities. We release our code and any non-protected data.

arXiv:2509.22989v2 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated strong persuasive capabilities comparable to those of humans, offering promising benefits while raising societal concerns. However, systematically evaluating the persuasive capabilities of LLMs is inherently challenging, as the effectiveness of persuasion among humans varies significantly across different domains. In this paper, we take a theory-driven approach to provide a scalable and principled framework for studying the persuasive capabilities of LLMs. Grounded in Bayesian persuasion theory, we repurpose human-human persuasion datasets to construct environments for evaluating and training LLMs as strategic persuaders. Our results reveal that frontier models can consistently achieve high persuasion gains and exhibit sophisticated persuasion strategies that align with theoretical characterizations. Building on this, we use reinforcement learning to train LLMs for strategic persuasion in our environments. Our results also demonstrate that even small LLMs can obtain significantly higher persuasion gains through reinforcement learning.