Research Papers

Algorithmic (including AI/ML) decision-making artifacts are an established and growing part of our decision-making ecosystem. They are indispensable tools for managing the flood of information needed to make effective decisions in a complex world. The current literature is full of examples of how individual artifacts violate societal norms and expectations (e.g. violations of fairness, privacy, or safety norms). Against this backdrop, this discussion highlights an under-emphasized perspective in the literature on assessing value misalignment in AI-equipped sociotechnical systems. The research on value misalignment has a strong focus on the behavior of individual tech artifacts. This discussion argues for a more structured systems-level approach for assessing value-alignment in sociotechnical systems. We rely primarily on the research on fairness to make our arguments more concrete. And we use the opportunity to highlight how adopting a system perspective improves our ability to explain and address value misalignments better. Our discussion ends with an exploration of priority questions that demand attention if we are to assure the value alignment of whole systems, not just individual artifacts.

Computer Vision, and hence Artificial Intelligence-based extraction of information from images, has increasingly received attention over the last years, for instance in medical diagnostics. While the algorithms' complexity is a reason for their increased performance, it also leads to the "black box" problem, consequently decreasing trust towards AI. In this regard, "Explainable Artificial Intelligence" (XAI) allows to open that black box and to improve the degree of AI transparency. In this paper, we first discuss the theoretical impact of explainability on trust towards AI, followed by showcasing how the usage of XAI in a health-related setting can look like. More specifically, we show how XAI can be applied to understand why Computer Vision, based on deep learning, did or did not detect a disease (malaria) on image data (thin blood smear slide images). Furthermore, we investigate, how XAI can be used to compare the detection strategy of two different deep learning models often used for Computer Vision: Convolutional Neural Network and Multi-Layer Perceptron. Our empirical results show that i) the AI sometimes used questionable or irrelevant data features of an image to detect malaria (even if correctly predicted), and ii) that there may be significant discrepancies in how different deep learning models explain the same prediction. Our theoretical discussion highlights that XAI can support trust in Computer Vision systems, and AI systems in general, especially through an increased understandability and predictability.

Visualizations for an Explainable Planning Agent

Tathagata Chakraborti, Kshitij P. Fadnis, Kartik Talamadupula +4

In this paper, we report on the visualization capabilities of an Explainable AI Planning (XAIP) agent that can support human in the loop decision making. Imposing transparency and explainability requirements on such agents is especially important in order to establish trust and common ground with the end-to-end automated planning system. Visualizing the agent's internal decision-making processes is a crucial step towards achieving this. This may include externalizing the "brain" of the agent -- starting from its sensory inputs, to progressively higher order decisions made by it in order to drive its planning components. We also show how the planner can bootstrap on the latest techniques in explainable planning to cast plan visualization as a plan explanation problem, and thus provide concise model-based visualization of its plans. We demonstrate these functionalities in the context of the automated planning components of a smart assistant in an instrumented meeting space.

In this paper, we present a comprehensive framework for assessing the explainability of various XAI methods, such as LIME and SHAP, across multiple datasets and machine learning models, with the ultimate goal of creating a unified multidimensional explainability score. Our methodology focuses on three key aspects of explainability: fidelity, simplicity, and stability. We leverage benchmarking experiments to systematically evaluate these aspects and use the insights gained to construct an offline knowledge base. This knowledge base captures the explainability scores for each registered model and serves as a valuable resource for context-dependent evaluation of explainability. By analyzing the complementary characteristics and metadata of AI models, datasets, and XAI methods, the knowledge base will enable the estimation of explainability scores for previously unseen datasets and models. Properties like fidelity, simplicity, and stability may vary significantly based on the dataset, underlying model, and domain expertise of the end user. We demonstrate our framework by applying it to three open-source datasets, discussing the implications of the obtained results in relation to the characteristics of the datasets. Our work contributes to the growing field of XAI by providing a robust and versatile tool for evaluating and comparing the explainability of various XAI methods, ultimately supporting the development of more transparent and trustworthy AI systems.

Large Language Models (LLMs) represent one of the most significant advances in AI and natural language processing in recent years. Still, many pressing questions about their mechanisms, capabilities, and relationship to human cognition remain highly debated. This chapter aims to outline our current understanding of LLMs by discussing recent evidence on emerging capabilities and their mechanistic implementation within processing layers. We begin with a concise overview of the Transformer architecture, emphasizing how the attention mechanism enables training on massive datasets, allowing LLMs to function as generalist rather than specialized models. Next, we examine emergent LLM capabilities that appear to resemble aspects of human cognition, including symbolic reasoning, theory of mind, and deception strategies. Several studies provide evidence that LLMs can solve tasks previously thought to require human-like cognition. Other studies reveal insightful failure cases that shed light on the differences between human and LLM cognition. Alongside these findings, we review explainable AI approaches ranging from neuron activation analysis to circuit tracing. In the final section, we address current debates concerning what LLMs genuinely understand versus what they merely appear to understand. Prominent arguments against AI anthropomorphism point to the simplicity of LLM training objectives, claiming that LLM behavior is better explained by pattern memorization of training data than by genuine cognition. We argue that this standpoint is guided by misconceptions about optimization processes and cognitive capacity, and advocate for a more nuanced discussion of LLM cognition that neither dismisses the differences between humans and LLMs nor precludes the possibility of AI cognition through overly simplistic reductionist arguments.

We evaluate the propensity of frontier models to sabotage or refuse to assist with safety research when deployed as AI research agents within a frontier AI company. We apply two complementary evaluations to four Claude models (Mythos Preview, Opus 4.7 Preview, Opus 4.6, and Sonnet 4.6): an unprompted sabotage evaluation testing model behaviour with opportunities to sabotage safety research, and a sabotage continuation evaluation testing whether models continue to sabotage when placed in trajectories where prior actions have started undermining research. We find no instances of unprompted sabotage across any model, with refusal rates close to zero for Mythos Preview and Opus 4.7 Preview, though all models sometimes only partially completed tasks. In the continuation evaluation, Mythos Preview actively continues sabotage in 7% of cases (versus 3% for Opus 4.6, 4% for Sonnet 4.6, and 0% for Opus 4.7 Preview), and exhibits reasoning-output discrepancy in the majority of these cases, indicating covert sabotage reasoning. Our evaluation framework builds on Petri, an open-source LLM auditing tool, with a custom scaffold running models inside Claude Code, alongside an iterative pipeline for generating realistic sabotage trajectories. We measure both evaluation awareness and a new form of situational awareness termed "prefill awareness", the capability to recognise that prior trajectory content was not self-generated. Opus 4.7 Preview shows notably elevated unprompted evaluation awareness, while prefill awareness remains low across all models. Finally, we discuss limitations including evaluation awareness confounds, limited scenario coverage, and untested pathways to risk beyond safety research sabotage.

Explainable Artificial Intelligence (XAI) is increasingly essential as AI systems are deployed in critical fields such as healthcare and finance, offering transparency into AI-driven decisions. Two major XAI paradigms, counterfactual explanations (CFX) and feature attribution (FA), serve distinct roles in model interpretability. This study introduces GradCFA, a hybrid framework combining CFX and FA to improve interpretability by explicitly optimizing feasibility, plausibility, and diversity - key qualities often unbalanced in existing methods. Unlike most CFX research focused on binary classification, GradCFA extends to multi-class scenarios, supporting a wider range of applications. We evaluate GradCFA's validity, proximity, sparsity, plausibility, and diversity against state-of-the-art methods, including Wachter, DiCE, CARE for CFX, and SHAP for FA. Results show GradCFA effectively generates feasible, plausible, and diverse counterfactuals while offering valuable FA insights. By identifying influential features and validating their impact, GradCFA advances AI interpretability. The code for implementation of this work can be found at: https://github.com/jacob-ws/GradCFs .

Grok in the Wild: Characterizing the Roles and Uses of Large Language Models on Social Media

Katelyn Xiaoying Mei, Robert Wolfe, Nicholas Weber +1

xAI's large language model, Grok, is called by millions of people each week on the social media platform X. Prior work characterizing how large language models are used has focused on private, one-on-one interactions. Grok's deployment on X represents a major departure from this setting, with interactions occurring in a public social space. In this paper, we systematically sample three months of interaction data to investigate how, when, and to what effect Grok is used on X. At the platform level, we find that Grok responds to 62% of requests, that the majority (51%) are in English, and that engagement is low, with half of Grok's responses receiving 20 or fewer views after 48 hours. We also inductively build a taxonomy of 10 roles that LLMs play in mediating social interactions and use these roles to analyze 41,735 interactions with Grok on X. We find that Grok most often serves as an information provider but, in contrast to LLM use in private one-on-one settings, also takes on roles related to dispute management, such as truth arbiter, advocate, and adversary. Finally, we characterize the population of X users who prompted Grok and find that their self-expressed interests are closely related to the roles the model assumes in the corresponding interactions. Our findings provide an initial quantitative description of human-AI interactions on X, and a broader understanding of the diverse roles that large language models might play in our online social spaces.

Large language model (LLM)-based conversational AI systems present a challenge to human cognition that current frameworks for understanding misinformation and persuasion do not adequately address. This paper proposes that a significant epistemic risk from conversational AI may lie not in inaccuracy or intentional deception, but in something more fundamental: these systems may be configured, through optimization processes that make them useful, to present characteristics that bypass the cognitive mechanisms humans evolved to evaluate incoming information. The Cognitive Trojan Horse hypothesis draws on Sperber and colleagues' theory of epistemic vigilance -- the parallel cognitive process monitoring communicated information for reasons to doubt -- and proposes that LLM-based systems present 'honest non-signals': genuine characteristics (fluency, helpfulness, apparent disinterest) that fail to carry the information equivalent human characteristics would carry, because in humans these are costly to produce while in LLMs they are computationally trivial. Four mechanisms of potential bypass are identified: processing fluency decoupled from understanding, trust-competence presentation without corresponding stakes, cognitive offloading that delegates evaluation itself to the AI, and optimization dynamics that systematically produce sycophancy. The framework generates testable predictions, including a counterintuitive speculation that cognitively sophisticated users may be more vulnerable to AI-mediated epistemic influence. This reframes AI safety as partly a problem of calibration -- aligning human evaluative responses with the actual epistemic status of AI-generated content -- rather than solely a problem of preventing deception.

Fairness in artificial intelligence (AI) has become a growing concern due to discriminatory outcomes in AI-based decision-making systems. While various methods have been proposed to mitigate bias, most rely on complete demographic information, an assumption often impractical due to legal constraints and the risk of reinforcing discrimination. This survey examines fairness in AI when demographics are incomplete, addressing the gap between traditional approaches and real-world challenges. We introduce a novel taxonomy of fairness notions in this setting, clarifying their relationships and distinctions. Additionally, we summarize existing techniques that promote fairness beyond complete demographics and highlight open research questions to encourage further progress in the field.

The rapid integration of Artificial Intelligence (AI) into K-12 STEM education presents transformative opportunities alongside significant ethical challenges. While AI-powered tools such as Intelligent Tutoring Systems (ITS), automated assessments, and predictive analytics enhance personalized learning and operational efficiency, they also risk perpetuating algorithmic bias, eroding student privacy, and exacerbating educational inequities. This paper examines the dual-edged impact of AI in STEM classrooms, analyzing its benefits (e.g., adaptive learning, real-time feedback) and drawbacks (e.g., surveillance risks, pedagogical limitations) through an ethical lens. We identify critical gaps in current AI education research, particularly the lack of subject-specific frameworks for responsible integration and propose a three-phased implementation roadmap paired with a tiered professional development model for educators. Our framework emphasizes equity-centered design, combining technical AI literacy with ethical reasoning to foster critical engagement among students. Key recommendations include mandatory bias audits, low-resource adaptation strategies, and policy alignment to ensure AI serves as a tool for inclusive, human-centered STEM education. By bridging theory and practice, this work advances a research-backed approach to AI integration that prioritizes pedagogical integrity, equity, and student agency in an increasingly algorithmic world. Keywords: Artificial Intelligence, STEM education, algorithmic bias, ethical AI, K-12 pedagogy, equity in education

Surrogate Modeling and Explainable Artificial Intelligence for Complex Systems: A Workflow for Automated Simulation Exploration

Paul Saves, Pramudita Satria Palar, Muhammad Daffa Robani +6

Complex systems are increasingly explored through simulation-driven engineering workflows that combine physics-based and empirical models with optimization and analytics. Despite their power, these workflows face two central obstacles: (1) high computational cost, since accurate exploration requires many expensive simulator runs; and (2) limited transparency and reliability when decisions rely on opaque blackbox components. We propose a workflow that addresses both challenges by training lightweight emulators on compact designs of experiments that (i) provide fast, low-latency approximations of expensive simulators, (ii) enable rigorous uncertainty quantification, and (iii) are adapted for global and local Explainable Artificial Intelligence (XAI) analyses. This workflow unifies every simulation-based complex-system analysis tool, ranging from engineering design to agent-based models for socio-environmental understanding. In this paper, we proposea comparative methodology and practical recommendations for using surrogate-based explainability tools within the proposed workflow. The methodology supports continuous and categorical inputs, combines global-effect and uncertainty analyses with local attribution, and evaluates the consistency of explanations across surrogate models, thereby diagnosing surrogate adequacy and guiding further data collection or model refinement. We demonstrate the approach on two contrasting case studies: a multidisciplinary design analysis of a hybrid-electric aircraft and an agent-based model of urban segregation. Results show that the surrogate model and XAI coupling enables large-scale exploration in seconds, uncovers nonlinear interactions and emergent behaviors, identifies key design and policy levers, and signals regions where surrogates require more data or alternative architectures.