Research Papers

The intersection of Safety of Intended Functionality (SOTIF) and Functional Safety (FuSa) analysis of driving automation features has traditionally excluded Quality Management (QM) components (components that has no ASIL requirements allocated from vehicle-level HARA) from rigorous safety impact evaluations. While QM components are not typically classified as safety-relevant, recent developments in artificial intelligence (AI) integration reveal that such components can contribute to SOTIF-related hazardous risks. Compliance with emerging AI safety standards, such as ISO/PAS 8800, necessitates re-evaluating safety considerations for these components. This paper examines the necessity of conducting holistic safety analysis and risk assessment on AI components, emphasizing their potential to introduce hazards with the capacity to violate risk acceptance criteria when deployed in safety-critical driving systems, particularly in perception algorithms. Using case studies, we demonstrate how deficiencies in AI-driven perception systems can emerge even in QM-classified components, leading to unintended functional behaviors with critical safety implications. By bridging theoretical analysis with practical examples, this paper argues for the adoption of comprehensive FuSa, SOTIF, and AI standards-driven methodologies to identify and mitigate risks in AI components. The findings demonstrate the importance of revising existing safety frameworks to address the evolving challenges posed by AI, ensuring comprehensive safety assurance across all component classifications spanning multiple safety standards.

Alignment research focuses on making individual AI systems reliable. Human institutions achieve reliable collective behaviour differently: they mitigate the risk posed by misaligned individuals through organisational structure. Multi-agent AI systems should follow this institutional model using compartmentalisation and adversarial review to achieve reliable outcomes through architectural design rather than assuming individual alignment. We demonstrate this approach through the Perseverance Composition Engine, a multi-agent system for document composition. The Composer drafts text, the Corroborator verifies factual substantiation with full source access, and the Critic evaluates argumentative quality without access to sources: information asymmetry enforced by system architecture. This creates layered verification: the Corroborator detects unsupported claims, whilst the Critic independently assesses coherence and completeness. Observations from 474 composition tasks (discrete cycles of drafting, verification, and evaluation) exhibit patterns consistent with the institutional hypothesis. When assigned impossible tasks requiring fabricated content, this iteration enabled progression from attempted fabrication toward honest refusal with alternative proposals--behaviour neither instructed nor individually incentivised. These findings motivate controlled investigation of whether architectural enforcement produces reliable outcomes from unreliable components. This positions organisational theory as a productive framework for multi-agent AI safety. By implementing verification and evaluation as structural properties enforced through information compartmentalisation, institutional design offers a route to reliable collective behaviour from unreliable individual components.

Are AI Capabilities Increasing Exponentially? A Competing Hypothesis

Haosen Ge, Hamsa Bastani, Osbert Bastani

Rapidly increasing AI capabilities have substantial real-world consequences, ranging from AI safety concerns to labor market consequences. The Model Evaluation & Threat Research (METR) report argues that AI capabilities have exhibited exponential growth since 2019. In this note, we argue that the data does not support exponential growth, even in shorter-term horizons. Whereas the METR study claims that fitting sigmoid/logistic curves results in inflection points far in the future, we fit a sigmoid curve to their current data and find that the inflection point has already passed. In addition, we propose a more complex model that decomposes AI capabilities into base and reasoning capabilities, exhibiting individual rates of improvement. We prove that this model supports our hypothesis that AI capabilities will exhibit an inflection point in the near future. Our goal is not to establish a rigorous forecast of our own, but to highlight the fragility of existing forecasts of exponential growth.

Explainable Artificial Intelligence (XAI) has gained importance in interpreting model predictions. Among leading techniques for XAI, Local Interpretable Model-agnostic Explanations (LIME) is most frequently utilized as it notably helps people's understanding of complex models. However, LIME's analysis is constrained to a single image at a time. Besides, it lacks interaction mechanisms for observing the LIME's results and direct manipulations of factors affecting the results. To address these issues, we introduce an interactive visualization tool, LIMEVis, which improves the analysis workflow of LIME by enabling users to explore multiple LIME results simultaneously and modify them directly. With LIMEVis, we could conveniently identify common features in images that a model seems to mainly consider for category classification. Additionally, by interactively modifying the LIME results, we could determine which segments in an image influence the model's classification.

Comparing Explanations is Not Enough, Explain the Change: New Standards are Needed to Explain Behavioral Shifts in Large Language Models

Martino Ciaperoni, Marzio Di Vece, Roberto Pellungrini +3

Large-scale foundation models exhibit behavioral shifts when subjected to interventions such as scaling, fine-tuning, reinforcement learning with human feedback, or in-context learning. Current explainability methods are structurally ill-suited to explain these shifts, because they either treat models as static objects, as traditional eXplainable AI (XAI) approaches do, or merely compare independent explanations across different checkpoints of a model. As a result, these approaches fail to explain the functional transition between two model instances in which a certain behavior has shifted following an intervention. This gap creates significant governance risks across jurisdictions including the EU AI Act, US state legislation, and Chinese AI regulations, which require documenting causal chains for substantial system modifications. This position paper argues that explaining behavioral shifts in large language models requires a principled approach that treats the shift itself as the primary object of explanation: namely, one that explains how and why an intervention transforms a reference model into an updated model with different behavior. To support this claim, we introduce Comparative XAI (XAI$_Δ$), a novel XAI paradigm aimed at explaining the difference between two model checkpoints where a behavior has shifted, together with a set of desiderata specifying what XAI$_Δ$ explainers and explanations must satisfy, including comparability, validity, actionability, and monitoring, with the goal of grounding model auditing in explicit, measurable requirements. Finally, we provide preliminary evidence suggesting the need for XAI$_Δ$ in practice through illustrative experiments, compiling the resulting findings into a transition report directly usable for governance and incident documentation.

PyGALAX is a Python package for geospatial analysis that integrates automated machine learning (AutoML) and explainable artificial intelligence (XAI) techniques to analyze spatial heterogeneity in both regression and classification tasks. It automatically selects and optimizes machine learning models for different geographic locations and contexts while maintaining interpretability through SHAP (SHapley Additive exPlanations) analysis. PyGALAX builds upon and improves the GALAX framework (Geospatial Analysis Leveraging AutoML and eXplainable AI), which has proven to outperform traditional geographically weighted regression (GWR) methods. Critical enhancements in PyGALAX from the original GALAX framework include automatic bandwidth selection and flexible kernel function selection, providing greater flexibility and robustness for spatial modeling across diverse datasets and research questions. PyGALAX not only inherits all the functionalities of the original GALAX framework but also packages them into an accessible, reproducible, and easily deployable Python toolkit while providing additional options for spatial modeling. It effectively addresses spatial non-stationarity and generates transparent insights into complex spatial relationships at both global and local scales, making advanced geospatial machine learning methods accessible to researchers and practitioners in geography, urban planning, environmental science, and related fields.

Artificial intelligence (AI) and Machine Learning (ML) have moved from research and pilot projects into everyday business operations, with generative AI accelerating adoption across processes, products, and services. This paper introduces the concept of Responsible AI for organizational practice, with a particular focus on small and medium-sized enterprises. It structures Responsible AI along four focal areas that are central for introducing and operating AI systems in a legally compliant, comprehensible, sustainable, and data-sovereign manner. First, it discusses the EU AI Act as a risk-based regulatory framework, including the distinction between provider and deployer roles and the resulting obligations such as risk assessment, documentation, transparency requirements, and AI literacy measures. Second, it addresses Explainable AI as a basis for transparency and trust, clarifying key notions such as transparency, interpretability, and explainability and summarizing practical approaches to make model behavior and decisions more understandable. Third, it covers Green AI, emphasizing that AI systems should be evaluated not only by performance but also by energy and resource consumption, and outlines levers such as model reuse, resource-efficient adaptation, continuous learning, model compression, and monitoring. Fourth, it examines local models (on-premise and edge) as an operating option that supports data protection, control, low latency, and strategic independence, including domain adaptation via fine-tuning and retrieval-augmented generation. The paper concludes with a consolidated set of next steps for establishing governance, documentation, secure operation, sustainability considerations, and an implementation roadmap.

As AI systems evolve from isolated predictors into complex, heterogeneous ecosystems of foundation models and specialized adapters, distinguishing genuine behavioral novelty from functional redundancy becomes a critical governance challenge. Here, we introduce a statistical framework for auditing model uniqueness based on In-Silico Quasi-Experimental Design (ISQED). By enforcing matched interventions across models, we isolate intrinsic model identity and quantify uniqueness as the Peer-Inexpressible Residual (PIER), i.e. the component of a target's behavior strictly irreducible to any stochastic convex combination of its peers, with vanishing PIER characterizing when such a routing-based substitution becomes possible. We establish the theoretical foundations of ecosystem auditing through three key contributions. First, we prove a fundamental limitation of observational logs: uniqueness is mathematically non-identifiable without intervention control. Second, we derive a scaling law for active auditing, showing that our adaptive query protocol achieves minimax-optimal sample efficiency ($dσ^2γ^{-2}\log(Nd/δ)$). Third, we demonstrate that cooperative game-theoretic methods, such as Shapley values, fundamentally fail to detect redundancy. We implement this framework via the DISCO (Design-Integrated Synthetic Control) estimator and deploy it across diverse ecosystems, including computer vision models (ResNet/ConvNeXt/ViT), large language models (BERT/RoBERTa), and city-scale traffic forecasters. These results move trustworthy AI beyond explaining single models: they establish a principled, intervention-based science of auditing and governing heterogeneous model ecosystems.

Recent work identifies a stated-revealed (SvR) preference gap in language models (LMs): a mismatch between the values models endorse and the choices they make in context. Existing evaluations rely heavily on binary forced-choice prompting, which entangles genuine preferences with artifacts of the elicitation protocol. We systematically study how elicitation protocols affect SvR correlation across 24 LMs. Allowing neutrality and abstention during stated preference elicitation allows us to exclude weak signals, substantially improving Spearman's rank correlation ($ρ$) between volunteered stated preferences and forced-choice revealed preferences. However, further allowing abstention in revealed preferences drives $ρ$ to near-zero or negative values due to high neutrality rates. Finally, we find that system prompt steering using stated preferences during revealed preference elicitation does not reliably improve SvR correlation on AIRiskDilemmas. Together, our results show that SvR correlation is highly protocol-dependent and that preference elicitation requires methods that account for indeterminate preferences.

Machine learning models in high-stakes applications, such as recidivism prediction and automated personnel selection, often exhibit systematic performance disparities across sensitive subpopulations, raising critical concerns regarding algorithmic bias. Fairness auditing addresses these risks through two primary functions: certification, which verifies adherence to fairness constraints; and flagging, which isolates specific demographic groups experiencing disparate treatment. However, existing auditing techniques are frequently limited by restrictive distributional assumptions or prohibitive computational overhead. We propose a novel empirical likelihood-based (EL) framework that constructs robust statistical measures for model performance disparities. Unlike traditional methods, our approach is non-parametric; the proposed disparity statistics follow asymptotically chi-square or mixed chi-square distributions, ensuring valid inference without assuming underlying data distributions. This framework uses a constrained optimization profile that admits stable numerical solutions, facilitating both large-scale certification and efficient subpopulation discovery. Empirically, the EL methods outperform bootstrap-based approaches, yielding coverage rates closer to nominal levels while reducing computational latency by several orders of magnitude. We demonstrate the practical utility of this framework on the COMPAS dataset, where it successfully flags intersectional biases, specifically identifying a significantly higher positive prediction rate for African-American males under 25 and a systemic under-prediction for Caucasian females relative to the population mean.

A core assumption of Explainable AI (XAI) is that explanations are useful to users -- that is, users will do something with the explanations. Prior work, however, does not clearly connect the information provided in explanations to user actions to evaluate effectiveness. In this paper, we articulate this connection. We conducted a formative study through 14 interviews with end users in education and medicine. We contribute a catalog of information and associated actions. Our catalog maps 12 categories of information that participants described relying on to take 60 different actions. We show how AI Creators can use the catalog's specificity and breadth to articulate how they expect information in their explanations to lead to user actions and test their assumptions. We use an exemplar XAI system to illustrate this approach. We conclude by discussing how our catalog expands the design space for XAI systems to support actionability.

AI systems are increasingly used in high-stakes domains such as credit rating, where fairness concerns are critical. Existing fairness assessments are typically conducted by AI experts or regulators using predefined protected attributes and metrics, which often fail to capture the diversity and nuance of fairness notions held by the individuals who are affected by these systems' decisions, such as decision subjects. Recent work has therefore called for involving affected individuals in fairness assessment, yet little empirical evidence exists on how they create their own fairness criteria or what kinds of criteria they produce - knowledge that could not only inform experts' fairness evaluation and mitigation, but also guide the design of AI assessment tools. We address this gap through a qualitative user study with 18 participants in a credit rating scenario. Participants first articulated their fairness notions in their own words. Then, participants turned them into concrete quantified and operationalized fairness criteria, through an interactive prototype we designed. Our findings provide empirical evidence of the process through which people's fairness notions emerge via grounding in model features, and uncover a diverse set of individuals' custom-defined criteria for both outcome and procedural fairness. We provide design implications for processes and tools that support more inclusive and value-sensitive AI fairness assessment.