Research Papers

The widespread integration of Large Language Models (LLMs) necessitates rigorous and systematic safety evaluation. Existing paradigms either rely on constructed benchmarks to assess safety from predefined perspectives, or employ dynamic red-teaming to probe potential vulnerabilities. While effective, these approaches face challenges, as they depend heavily on expert domain knowledge, offer limited systematic guarantees, and are vulnerable to rapid obsolescence. To address these limitations, we introduce a novel framework POLARIS that brings the rigor of specification-based software testing to AI safety. POLARIS first compiles unstructured natural-language policies into First-Order Logic (FOL) representations, establishing a traceable link between high-level rules and concrete test cases. This formalization enables the construction of a Semantic Policy Graph, where complex policy violation scenarios are encoded as traversable paths. By systematically exploring this graph, POLARIS uncovers compositional violation patterns, which are then instantiated into executable natural-language test queries, enabling coverage-driven and reproducible safety testing. Experiments demonstrate that POLARIS achieves higher policy coverage and attack success counts compared to established baselines. Crucially, by bridging formal methods and AI safety, POLARIS provides a principled, automated approach to ensuring LLMs adhere to safety-critical policies with verifiable traceability. We release our code at https://github.com/huac-lxy/POLARIS.

Retinal imaging provides a non-invasive window into systemic microvascular health and has emerged as a potential biomarker for systemic diseases. However, whether retinal features encode biologically meaningful systemic signals that can be reliably interpreted using explainable artificial intelligence (XAI) remains unclear. An explainable multi-task deep learning framework was developed to investigate associations between retinal microvascular features and systemic abnormalities in Type 2 Diabetes Mellitus. A total of 11,011 fundus images from 2,719 individuals were analysed using a shared neural network with task-specific heads for glycaemic status, kidney abnormality, and multi-system involvement. Model interpretability was evaluated using Gradient-weighted Class Activation Mapping (Grad-CAM), anatomical masking, and vessel alignment analysis. The framework demonstrated task-dependent predictive performance, with the best discrimination observed for kidney abnormality (AUC up to 0.63), whereas glycaemic status prediction showed limited performance (AUC = 0.49-0.61). Explainability analyses consistently localized model attention to retinal vessels and peripapillary regions. Masking experiments showed that occlusion of vascular regions caused the greatest performance decline, indicating that retinal vessels were the primary predictive source. Different architectures exhibited heterogeneous attention patterns, suggesting multiple representational pathways for systemic signal encoding. This pilot study demonstrates that retinal microvascular features contain measurable signals associated with systemic abnormalities, particularly microvascular damage. By integrating multi-task learning with quantitative XAI validation, this framework advances retinal imaging toward interpretable digital biomarkers for systemic risk stratification in diabetes.

Concerns about algorithmic bias and fairness have increased as artificial intelligence has been incorporated into high-stakes decision-making. Traditional Naive Bayes classifiers, while efficient and interpretable, lack fairness-awareness mechanisms and perpetuate historical biases in sensitive domains such as hiring, credit scoring, and criminal justice. This study develops a fairness-aware extension of the Naive Bayes classifier that mitigates bias while maintaining computational efficiency. We propose the Bias Mitigating Naive Bayes (BMNB) classifier, integrating in-processing and post-processing interventions. The in-processing stage employs a blended likelihood approach combining group-specific and pooled likelihood estimates through a tunable blending parameter alpha to balance fairness and accuracy. The post-processing stage applies output calibration with adaptive thresholding to fine-tune group-specific decision boundaries. Experimental results indicate that BMNB attains Disparate Impact (DI) values of 1.000, 1.171, and 0.997 and Equal Opportunity Difference (EOD) values of -0.217, -0.226, and -0.053 on the Adult, ProPublica, and Framingham datasets, respectively, while maintaining computational efficiency. Ablation studies confirm that the combination of blended likelihood and adaptive thresholding yields superior performance compared to either technique in isolation.

Real-World Data (RWD), with its large sample sizes and rich clinical detail, offers a compelling alternative to randomized controlled trials (RCTs) for studying treatment effects in diverse and complex patient populations. However, its observational nature introduces confounding that prevents straightforward comparative effectiveness research. Target trial emulation leverages RWD to estimate average treatment effects (ATE) at the population scale and diversity that RCTs cannot achieve, yet its validity depends critically on unbiased ATE estimation under high-dimensional confounding. Many causal inference pipelines address high-dimensional confounding through machine learning and artificial intelligence (ML/AI) outcome regression. However, commonly used ML/AI regression models exhibit systematic prediction bias, with predicted outcomes shrinking toward the marginal outcome mean. This structural bias propagates into ATE estimation and cannot be corrected by cross-fitting, ensemble methods, or any standard ML practice. In this work, we first quantitatively characterize how systematic prediction bias in ML/AI outcome regression leads to biased ATE estimates in causal inference models. We further propose an unbiased ML/AI regression-based causal inference framework to ensure unbiased ATE estimation for observational studies. We demonstrate our approach by studying the effects of opioids on cardiovascular health in patients with chronic pain using UK Biobank data.

While large-scale models such as LLMs and diffusion models have achieved practical success, public institutions have emphasized the importance of explainability in AI. Existing methods for explaining AI, however, are not designed to provide completely faithful explanations of the behavior of large-scale AI systems. Although a completely faithful and interpretable explanation of the behavior of an AI system might be useful for AI governance, it has not been known whether providing such an explanation is theoretically possible. In this paper, we mathematically prove a fundamental quadrilemma in explaining AI, stating that AI and its explanation cannot satisfy the following four conditions simultaneously: 1) the complexity of the operation environment, 2) the goodness of the AI's performance, 3) the interpretability of the AI's explanation, and 4) the complete faithfulness of the AI's explanation. This quadrilemma suggests that, in most applications where we cannot change the environment or sacrifice good AI performance and an interpretable explanation, we should give up complete faithfulness of explanations and should instead aim to explain only the parts that are important for applications. As a consequence, the quadrilemma implies that AI governance should be designed on the premise that the faithfulness of AI explanations is always incomplete.

Classical reinforcement learning assumes the agent interacts with a fixed environment whose behavior does not depend on the agent's policy. This assumption breaks down in non-realizable settings where other actors might anticipate the agent's behavior, including environments crucial to AI safety, where the agent interacts with predictors, humans, other AI agents, and institutions. In such settings, the agent's model class fails to capture the world in which it operates. Under such misspecification, classical Bayesian methods can produce confidently wrong posteriors, unreliable decisions, and unbounded regret, as realizability fails to obtain. Infra-Bayesianism is a decision-theoretic framework that addresses these failures by distinguishing ordinary probabilistic uncertainty, where priors can be reasonably chosen, from Knightian uncertainty, where no grounds exist for the construction of such a prior. It does so by evaluating actions on their worst-case outcomes, rather than from posterior expectations or weighted averaging. We present the first proof-of-concept implementation of an infra-Bayesian reinforcement learning architecture for finite-outcome stateless decision problems. Our agent maintains a set of imprecise hypotheses, updates them using infra-Bayesian conditioning, and selects actions by maximizing worst-case expected value. We apply this implementation of the infra-Bayesian maximin decision process to an environment with Knightian uncertainty, and demonstrate a lower worst-case regret as compared to classical reinforcement learning agents. We also investigate Newcomb's problem and show that the infra-Bayesian agent picks the optimal strategy, outperforming classical decision theory agents. Our results provide a step towards reinforcement learning agents that remain robust under model misspecification and policy-dependent uncertainty.

Enhancing Deep Neural Network Reliability with Refinement and Calibration

Ramya Hebbalaguppe, Ajay Shastry, Soumya Suvra Ghosal +1

Although deep neural networks (DNNs) achieve high predictive accuracy, their confidence estimates are often unreliable, potentially compromising user trust in their decisions. This has motivated research on calibrated models, where calibration measures how well a model's predicted confidence aligns with the empirical probability of correctness. However, calibration metrics can often be improved through post-processing techniques that merely mimic training-time uncertainty without genuinely improving the model's understanding. For this reason, statisticians recommend that models be not only calibrated but also refined. Intuitively, a model is considered more refined if it assigns significantly different confidence scores to correct and incorrect predictions, a property also referred to as sharpness. We observe that many existing calibration methods improve calibration at the cost of reduced refinement. To address this limitation, we propose: (1) a novel loss function that explicitly promotes refinement and can be optimized through supervised contrastive learning; and (2) a unified training framework, RefCal, that jointly optimizes calibration, refinement, and accuracy to improve DNN reliability. On the CIFAR-100-LT dataset with 10 percent class imbalance, RefCal achieves (accuracy, refinement, ECE) of (58.81, 95.67, 0.08), substantially outperforming the widely used Correctness Ranking Loss, which achieves (46.27, 93.7, 0.22).

AI-enabled services deployed in critical digital infrastructure are subject to governance obligations spanning transparency, accountability, fairness, and traceability. Compliance today remains documentation-centric: obligations are described in prose, audits rely on static checklists, and verification depends on manual review. Such approaches do not scale to automated AI systems. This paper introduces Ontological Knowledge Blocks (OKBs), a programmable governance infrastructure that compiles regulatory obligations into machine-checkable constraints over structured evidence graphs. We formalize an OKB as a 5-tuple that binds normative obligations to an RDF/OWL concept schema, executable SHACL validation rules, explicit evidence requirements, and PROV-O provenance links. A deterministic regulatory compiler translates structured Intermediate Representation (IR) records into composable KB modules, enabling profile-based governance reconfiguration without modifying service code. We implement two prototypes and evaluate them in an AI-assisted HPC resource allocation scenario across 24 validation runs and four governance profiles. Results demonstrate profile-sensitive validation, strictly additive violation accumulation, SHACL validation latency between 12.6 ms and 100.3 ms, and profile equivalence testing confirming Combined as the strictly most comprehensive profile. All artefacts are released as open source.

Illegal content reporting mechanisms are a key technical and organizational measure through which online platforms address illegal content under the European Union Digital Services Act (DSA). Article 16 requires user notices to be sufficiently substantiated and submitted in good faith, placing users in the difficult position of interpreting legal and procedural language and translating ambiguous content into legally meaningful categories and reasons. We investigate how large language model (LLM)-based assistants can support this reporting process. In a controlled user study (N = 450) using an interface modeled on a major platform reporting workflow, we compare three conditions: unaided reporting, a conventional explainable AI assistant (XAI) that suggests a single legal category with a rationale, and an evaluative AI assistant (EvalAI) that presents balanced pro and con arguments across candidate legal provisions. We further examine these assistance forms under systematically varied AI error regimes. Our results show that EvalAI improves provision-level accuracy under AI error and reduces misclassification distance relative to conventional XAI, particularly for near-miss and overbreadth errors. When AI output is correct, conventional XAI enables faster decisions, but neither AI assistance form reliably improves the quality of users' substantiated explanations relative to unaided reporting. We discuss design implications for compliance-oriented reporting interfaces, highlighting trade-offs between accuracy, deliberation, explanation quality, and vulnerability to misleading AI output.

Large language models (LLMs) have the potential to aid and improve human decision-making in classification tasks, not only by providing fairly accurate predictions, but also in their ability to generate cogent narrative explanations of those predictions. Prior work has demonstrated that people generally find AI narrative explanations to be understandable, trustworthy, and convincing for changing beliefs and opinions; however, less is known about the impact of narrative explanations on objective human decision-making performance. Here we conduct a large-scale human behavioral experiment to evaluate decision-making performance with LLM-generated narrative explanations of varying persuasiveness. We found the degree of persuasiveness, or lack thereof, for LLM-based explanations did not meaningfully impact decision accuracy over a simple AI prediction alone, in agreement with typical results with explainable AI based on feature importance. We found evidence that narratives increased reliance on AI, but both when the AI prediction was correct and incorrect. Exploratory analyses also indicated that the more persuasive narratives may have had a detrimental effect on decision response times and the ability to discriminate between a correct and incorrect AI prediction. Overall, this work indicates that including narrative explanations with AI predictions may involve tradeoffs for decision-making performance, and more work is needed to determine how and when narrative explanations impact human decision-making.

Modern Artificial Intelligence achieves remarkable predictive power by optimizing statistical risk functionals over vast corpora. Yet a gap separates this from genuine intelligence: the inability to distinguish correlation from causation. This paper argues that causal inference (identifying mechanisms invariant under intervention) is AI's indispensable statistical conscience. Without causal grounding, AI systems are correlation machines: powerful in familiar domains, brittle under distribution shift, and biased in high-stakes settings. Three contributions develop this argument. First, a Statistical Necessity Theorem for Causal Generalization: any algorithm achieving out-of-distribution generalization must encode causal structure, formalizing the distinction between prediction P(Y|X) and intelligence P(Y|do(X)). Second, a unified framework connects Pearl's do-calculus, the Potential Outcomes framework, Double Machine Learning, and Invariant Risk Minimization as a family of Causal Statistical Estimators, each identifying interventional distributions under different assumptions. Third, three AI failure modes (hallucination in large language models, reward hacking in reinforcement learning from human feedback, and degradation under distribution shift) are manifestations of causal blindness, each admitting a principled statistical remedy. Trustworthy AI is, at its core, a problem of causal statistics. The statistical community is not merely equipped to solve it -- it is the only community with the foundational tools to do so rigorously.

This paper investigates a unexplored yet impactful vulnerability in AI explainability used in intrusion detection (IDS): multicollinearity-induced instability. Despite extensive reliance on post-hoc explainability tools such as SHAP or LIME, the impact of correlated features on explanation robustness is not evaluated. We introduce a formal theorem stating that multicollinearity inflates attribution variance. This demonstrates that explanations and feature importances are non-identifiable under multicollinearity. A suite of comprehensive experiments validates the theorem on a representative benchmark dataset, UNSW-NB15. Four widely used families of models are evaluated, including linear, tree-based, kernel, and neural, across full and pruned feature sets based on VIF and correlation thresholding. We propose the novel metric of Explanability Fragility Score and two novel methods to mitigate it with variable integration complexity. CAA-Filtering focuses on stabilising explanations by grouping attributions of trained models. SHARP is a novel training-time regularisation framework that penalises attribution instability, enabling controllable and monotonic improvement of explainability stability. The findings support stable predictive performance, using Kendall's τ to quantify instability across bootstrapped explanations. This work has direct implications for the trustworthiness and reproducibility of XAI in security-critical contexts, and motivates incorporating multicollinearity mitigations into the IDS pipelines, providing a set of guidelines for practitioners.