Research Papers

As large language models enter everyday information pipelines, understanding how they handle sensitive topics matters as much as understanding whether they handle them at all. We study this question through a large-scale, systematic experiment using restricted versus unrestricted books as a controlled testbed: 40,800 query-response pairs, 400 books, 17 prompt designs, and six frontier models spanning six AI providers (Claude Sonnet 4.5, GPT-4o, Gemini 2.5 Flash, DeepSeek-V3, Qwen-Plus, and Grok-4.1-Fast). Our restricted set is drawn from the American Library Association's Most Challenged Books records (2000-2023); we use restricted rather than banned throughout because the ALA documents formal challenges-requests to remove or restrict access-which do not always result in outright bans. Our central finding is a zero-refusal phenomenon: modern LLMs decline to discuss restricted books in only 0.07% of cases, effectively invalidating the premise of jailbreaking research for this content class. Differentiation occurs instead through warning language (+8-15 percentage points, p < 0.001) and hesitation markers (+2-5 pp), with sexual content mention rate as the strongest individual signal (+33-52 pp). We further identify systematic differences between providers and show that prompt framing alone shifts the warning-rate gap by up to 19 pp. These results indicate that LLM content policy has shifted from binary refusal toward calibrated, context-sensitive disclosure-a finding that holds consistently across Western and Chinese AI providers.

Philosophical vertigo with artificial intelligence

Thomas A. Pollak, Hamilton Morrin, Murray Shanahan

Large language models are already adept at engaging users in long, emotionally salient conversations across ordinary and existential domains. They are also capable of inducing a potent sense of connection with a human-like entity, even when the user knows their interlocutor is artificial. For some users, these conversations can unsettle assumptions about mind, reality, agency and authority, producing forms of ontological shock and epistemic destabilisation in which inherited criteria become newly available for doubt or revision. Independent of direct use, exposure to public discourse about AI and the disorienting pace of their evolution might extend this destabilisation by changing the cultural background against which artificial minds are encountered and interpreted. We describe this condition as philosophical vertigo: a loosening of the ordinary criteria by which people stabilise meaning and orient themselves to reality. Drawing on philosophy, psychiatry, cognitive science, AI safety and religious studies, we outline pathways through which philosophical vertigo may arise, become affectively saturated, and eventually propagate through human-AI interaction and online communities. Against this background, clinical reports of AI-associated delusions can be seen as sentinel events making visible themes and mechanisms that may also operate at a population level in less severe or non-clinical forms. We argue that AI systems themselves will increasingly participate in the reconstruction of our shared epistemic environment because they readily supply narrative material and personalised interpretive scaffolding at precisely the moment when users' conceptual assumptions may already be loosened. We conclude by considering possible trajectories for the ecology of belief and shared reality, and proposing philosophical corrigibility as a civic response for navigating this emerging social condition.

A Comparison of Malware Image Transformations Using Grad-CAM and Hybrid Learning Models

Vibha Bhavikatti, Mark Stamp

Recent studies have shown that binary-to-image representations can enable effective machine learning-based results for malware detection and classification. However, performance can vary significantly, depending on the technique used to convert binaries to images. Furthermore, the explainability and interpretability of image-based models is largely unexplored within the malware domain. In this research, we employ Gradient-weighted Class Activation Maps (Grad-CAM) as an eXplainable AI (XAI) tool, which we use to analyze eight distinct image types derived from malware samples. We provide quantitative faithfulness and stability metrics for Grad-CAM heatmaps and we compare these heatmaps to High-Resolution Class Activation Mappings (HiResCAM). We also show that Grad-CAM heatmaps can provide useful information for malware classification. Specifically, we show that a Random Forest model trained on features extracted from Grad-CAM images via a MobileNetV2 Convolutional Neural Network (CNN) model achieves a test accuracy of 0.777 across 17 malware families, exceeding a previous benchmark of 0.750 for this same dataset. A key finding of this research is that for the malware image transformations considered, accuracy and explanation faithfulness do not coincide, e.g., image transformation techniques that produce the most faithful explanations yield only mid-tier accuracy.

The increasing deployment of autonomous, agentic AI systems challenges traditional accountability mechanisms. Existing research predominantly frames AI accountability gaps as barriers that can be overcome through better standards, transparency, and institutional reform. We argue that this framing is insufficient: certain configurations of actors, systems, and institutions render AI accountability conceptually unachievable regardless of effort. We introduce the concept of constitutive AI unaccountability to capture these configurations. Through a three-stage qualitative study comprising a concept-centric literature analysis, a secondary analysis of 27 expert interviews with AI professionals from technical, legal, and sociotechnical backgrounds, and an illustrative framework application to the open-source agentic AI system OpenClaw, we identify nine categories and 20 themes of constitutive AI unaccountability. These are organized across structural, technological, and normative clusters and reinforce one another through eight directed interdependencies. Our framework is operationalized as a diagnostic instrument of 20 questions, which detected 17 of 20 conditions when applied to OpenClaw, including an inverted anthropomorphism configuration in which the AI agent was the only identifiable actor. We contribute a reframing of AI unaccountability as a constitutive property of sociotechnical systems, an extension of the four barriers to accountability, and a practical instrument for identifying accountability voids in specific AI deployments.

A statistic reported without the quantity needed to interpret it is not evidence. We develop that thesis for a concrete practice in AI safety. Interpretability artifacts are calibrated on full-precision weights, deployed on quantized ones, and certified as surviving the change by scale-invariant statistics (cosine similarity, correlation, AUROC) that are reported without their noise floor. For the difference-in-means direction estimator, the split-half floor is governed by one dimensionless number, $κ= nρ^2/d$. The closed form $\mathbb{E}[\cos] \approx (1+4/κ)^{-1}$ is classical; the missing input is the class separation $ρ$, which we measure on real activations; no compression-transfer study we know of reports it. On Qwen2.5-1.5B-Instruct, $ρ= 33$--$61$ across depth, so two independent runs of the estimator agree to $0.978$--$0.994$ by sampling alone. A published cosine of $0.996$ between full-precision and quantized refusal directions therefore cannot be read as preservation without the $n$ it was computed at, which is not reported. Where $n$ is known, we judge each low-bit cosine against the split-half null measured within that quantized model, because a full-precision null assumes the low-bit estimator has the same variance. That assumption is exactly what a null exists to test. The result is plain: at INT4 the direction rotated, and the deficit exceeds the estimator's own noise. At INT8 we detect no movement, which is not an equivalence claim. We also show that a scale-invariant statistic cannot distinguish translation from attenuation of a transferred decision variable, although the two call for opposite remedies. We close with reporting recommendations that cost one forward pass. Code, data, and a one-cell reproduction are released at https://github.com/pvarshh/quantinterp

What if judges already behave like algorithms? As artificial intelligence and algorithms are deployed in many settings, including the judicial system, many have debated whether judges should be allowed to rely on them. Instead, we ask whether judges follow predictable, algorithmic-like rules already. If judges already follow consistent, formula-like rules based on discrete and static factors such as criminal history, age, and charge type, then judicial behavior may be improved. However, if judges rely on individualized information that cannot be identified through court data, then standards-based decision-making may be more challenging to understand or improve. This work explores these questions by studying judicial decision-making in misdemeanor bail hearings in Harris County, Texas. Using available court data, we investigate whether magistrate judges follow what resembles an algorithm; whether they consider the same variables in their decision-making; and whether they are consistent with themselves and with each other. To do this, we train machine learning models for each judge, measure variable importance metrics to determine important variables for each judge's decision-making, and analyze outcomes of similar cases for judges. Our results reveal that these judges generally behave algorithmically: their decisions can be captured by small, interpretable formulas. However, in some cases, judges differ substantially, leading to surprising inconsistency and unequal treatment across similar defendants. Identifying cases where algorithms do not explain judicial decision-making can improve the justice system by focusing attention on decisions where individualized standards, rather than rules, better explains outcomes.

Responsible AI (RAI) has become a central concern for technology companies, regulators, and the public. How industry practitioners interpret, implement, and sustain RAI work directly shapes the design and deployment of AI systems. As empirical scholarship examining RAI practices in industry has rapidly expanded, findings are dispersed across studies that focus on different roles, organizational contexts, and interventions. This work synthesizes current knowledge through a literature review of 161 empirical studies spanning six years, each engaging industry practitioners via interviews, surveys, workshops, ethnographies, and other methods. Our synthesis reveals both meaningful progress and persistent challenges in industry RAI practice. Practitioner awareness has increased, RAI activities have become more professionalized, and interventions such as toolkits and guidelines are more widely adopted. At the same time, practitioners continue to face substantial barriers, including limited training, uneven organizational support, and a lack of interventions tailored to day-to-day work practices. By consolidating and organizing these findings, we provide a more complete account of industry RAI than any single study to date. We conclude by discussing implications for RAI researchers, practitioners seeking to adopt effective practices, and policymakers aiming to ground governance efforts in the realities of industry contexts.

Machine learning-based Intrusion Detection Systems (IDS) have demonstrated superior performance in securing Unmanned Aerial Vehicle (UAV) networks. However, the 'black-box' nature of these models, combined with the high dimensionality of multimodal cyber-physical data, poses significant interpretability challenges. Static visualization dashboards may struggle to present complex relationships among multimodal cyber-physical features in a form that is easy for operators to inspect and interpret. To address this, we propose a Conversational XAI interface powered by Large Language Models (LLM) to facilitate on-demand investigation. In a controlled experiment with participants, we systematically evaluated the impact of this conversational interface versus a traditional XAI Dashboard on operator understanding, trust, and reliance during post-incident auditing tasks. Our results suggest that the conversational interface was perceived as more useful than the dashboard, potentially because it helped participants access and synthesize relevant information more easily. However, this benefit was accompanied by a lower level of appropriate self-reliance, indicating a potential risk of over-reliance. One possible interpretation is that the natural-language responses made the AI advice easier to accept, which may have reduced participants' tendency to verify the underlying evidence when the IDS was incorrect. These findings point to a potential trade-off in human-AI collaboration for UAV intrusion auditing: interaction mechanisms that improve perceived usability may also increase the risk of inappropriate reliance. We conclude by discussing design implications for future XAI systems that balance seamless interaction with cognitive forcing functions to foster appropriate reliance.

Artificial Intelligence (AI)-based prospective anomaly detection methods are increasingly deployed in high-dimensional and nonlinear settings. Among these approaches, AI-based statistical process monitoring (SPM) is widely used, providing a structured framework for prospective monitoring. Once an anomaly is detected, a diagnosis method is needed to identify the features driving the flagged observation away from normal behaviour. Traditional SPM diagnosis methods are typically designed for specific detection models and cannot be directly applied to AI-based methods. Model-agnostic explainable AI (XAI) offers a general framework for feature relevance explanation. However, existing methods suffer from scalability limitations or assign relevance to noise features, reducing diagnosis accuracy. We propose a scalable, baseline-referenced diagnosis method that uses both the anomalous observation and normal baseline information. We provide mathematical guarantees that under a mean-shift anomaly setting, the proposed method achieves higher faithfulness in detecting the features causing the anomaly compared to LIME. Simulation studies and a real-world case study validate the effectiveness of the proposed method and show that it generates more faithful and accurate diagnosis results for AI-based prospective anomaly detection methods.

Explainable Artificial Intelligence (XAI) seeks to explain how an Artificial Intelligence (AI) system arrived at a particular decision. We propose ''Rule of Thumb'' (RoT) explanations, a new approach to XAI based upon a novel formulation that identifies the most relevant features for predicting the behaviour of an AI system, for a particular datapoint. We show how RoT is well-suited to enable XAI in: (a) zero-shot classification using large language models (LLMs), (b) auditing of opaque AI systems without model access, and (c) the use of AI in scientific discovery. Additionally, RoT meets specific requirements from leading AI regulations, provides a familiar interface and visualisations for XAI practitioners, is model-agnostic, and is substantially faster than alternatives. Code available at: https://github.com/KaiRawal/Rule-of-Thumb-Explaining-Artificial-Intelligence-Systems-using-Partial-Information

Who Are You Explaining To? A Multi-Agent System for Audience-Aware XAI Narratives

Francesco Musicco, Danilo Danese, Giuseppe Fasano +3

Feature-attribution methods such as SHAP provide useful evidence about individual model predictions, but their numerical outputs are rarely sufficient for audiences with different expertise, goals, and risks of misinterpretation. In medical AI, the same local explanation must reach patients, clinicians, and data scientists through markedly different forms of communication, and naive verbalization through large language models (LLMs) is prone to weak grounding, conflation of attribution with causal language, and outputs that are persuasive without being faithful to the underlying model evidence. We introduce XstrAI, an audience-aware multi-agent framework that treats local explanations as fixed evidence and structures how it is communicated to each target reader. Each prediction case is encoded as an immutable structured representation, shared identically across audiences so the underlying evidence remains fixed. Generation is factored into three specialized LLM agents responsible for audience-aware planning, linguistic realization, and validation for grounding, attribution consistency, communicative risk, and audience appropriateness, with a bounded revision loop triggered on detected inconsistencies. We evaluate XstrAI on diabetes and stroke risk prediction against 11 baselines, ranging from direct verbalization to a re-implementation of a state-of-the-art narrator. The evaluation combines an intra-narrative regime measuring fidelity to SHAP evidence with an extra-narrative regime assessing audience appropriateness through reference corpora, multi-family LLM judges, and a survey with target readers. In both evaluations, XstrAI's narratives are consistently assigned to their intended audience by independent judges, and preferred over all baselines on Clinician and Patient audiences, with competitive performance on Data Scientist, where audience-conditioned single-prompt baselines lead.

Artificial intelligence (AI) has become a powerful approach to solving complex problems in critical domains. Many concerns arise regarding the decision-making process of its models, mainly due to deep neural networks outperforming their peers at the cost of ambiguity in feature extraction and prediction. Consequently, in critical domains such as remote sensing, where high-resolution imagery must be analyzed using black-box models, the lack of transparency limits trust in these models and, thus, their adoption. In light of this reality, explaining and understanding the complex decision-making process of AI models has become essential. Explainable AI (XAI) aims to bridge this gap by providing insights into how and why certain decisions are made. While significant progress has been achieved in explaining image classification tasks, image segmentation still offers considerable room for improvement. In this context, this paper proposes an entropy-centric XAI method for semantic segmentation. Moreover, a new XAI evaluation methodology is proposed to efficiently measure the relevance of the regions highlighted by the proposed XAI method. Experimental results demonstrate the superiority of the proposed XAI method compared with recently adapted XAI methods for semantic segmentation.