Research Papers

As machine learning models become increasingly integrated into healthcare, structural inequities and social biases embedded in clinical data can be perpetuated or even amplified by data-driven models. In survival analysis, censoring and time dynamics can further add complexity to fair model development. Additionally, algorithmic fairness approaches often overlook disparities in cross-group rankings, e.g., high-risk Black patients may be ranked below lower-risk White patients who do not experience the event of mortality. Such misranking can reinforce biological essentialism and undermine equitable care. We propose a Fairness-Aware Survival Modeling (FASM), designed to mitigate algorithmic bias regarding both intra-group and cross-group risk rankings over time. Using breast cancer prognosis as a representative case and applying FASM to SEER breast cancer data, we show that FASM substantially improves fairness while preserving discrimination performance comparable to fairness-unaware survival models. Time-stratified evaluations show that FASM maintains stable fairness over a 10-year horizon, with the greatest improvements observed during the mid-term of follow-up. Our approach enables the development of survival models that prioritize both accuracy and equity in clinical decision-making, advancing fairness as a core principle in clinical care.

Deep neural networks like PhaseNet show high accuracy in detecting microseismic events, but their black-box nature is a concern in critical applications. We apply Explainable Artificial Intelligence (XAI) techniques, such as Gradient-weighted Class Activation Mapping (Grad-CAM) and Shapley Additive Explanations (SHAP), to interpret the PhaseNet model's decisions and improve its reliability. Grad-CAM highlights that the network's attention aligns with P- and S-wave arrivals. SHAP values quantify feature contributions, confirming that vertical-component amplitudes drive P-phase picks while horizontal components dominate S-phase picks, consistent with geophysical principles. Leveraging these insights, we introduce a SHAP-gated inference scheme that combines the model's output with an explanation-based metric to reduce errors. On a test set of 9,000 waveforms, the SHAP-gated model achieved an F1-score of 0.98 (precision 0.99, recall 0.97), outperforming the baseline PhaseNet (F1-score 0.97) and demonstrating enhanced robustness to noise. These results show that XAI can not only interpret deep learning models but also directly enhance their performance, providing a template for building trust in automated seismic detectors. The implementation and scripts used in this study will be publicly available at https://github.com/ayratabd/xAI_PhaseNet.

Education in the era of generative AI faces a pivotal transformation. As AI systems reshape professional practices-from software development to creative design-educators must reconsider how to prepare students for a future where humans and machines co-construct knowledge. While tools like ChatGPT and Claude automate tasks and personalize learning, their educational potential depends on how meaningfully they are integrated into learning environments. This paper argues that Learning Management Systems (LMSs), as the core of educational practice, must evolve from static content repositories into dynamic ecosystems that cultivate higher-order thinking and meaningful human-AI interaction. We propose two guiding principles for integrating generative AI into LMSs. First, From Content Delivery to Fostering Higher-Order Thinking, emphasizing AI's role in supporting inquiry, collaboration, and reflective knowledge building. Second, Toward Meaningful Interaction with AI, highlighting the design of learning environments that nurture critical, intentional, and socially mediated engagement with AI. Drawing on a case study of CheckIT Learning, we illustrate how these principles can translate into practice. We conclude with the need for Edtech partnerships in an AI-powered world, underscoring that responsible AI integration in education requires sustained collaboration among researchers, educators, and technologists to ensure ethical, pedagogically grounded, and cognitively informed innovation.

In this study, we present an interpretable deep learning framework for the early detection of breast cancer using quantitative features extracted from digitized fine needle aspirate (FNA) images of breast masses. Our deep neural network, using ReLU activations, the Adam optimizer, and a binary cross-entropy loss, delivers state-of-the-art classification performance, achieving an accuracy of 0.992, precision of 1.000, recall of 0.977, and an F1 score of 0.988. These results substantially exceed the benchmarks reported in the literature. We evaluated the model under identical protocols against a suite of well-established algorithms (logistic regression, decision trees, random forests, stochastic gradient descent, K-nearest neighbors, and XGBoost) and found the deep model consistently superior on the same metrics. Recognizing that high predictive accuracy alone is insufficient for clinical adoption due to the black-box nature of deep learning models, we incorporated model-agnostic Explainable AI techniques such as SHAP and LIME to produce feature-level attributions and human-readable visualizations. These explanations quantify the contribution of each feature to individual predictions, support error analysis, and increase clinician trust, thus bridging the gap between performance and interpretability for real-world clinical use. The concave points feature of the cell nuclei is found to be the most influential feature positively impacting the classification task. This insight can be very helpful in improving the diagnosis and treatment of breast cancer by highlighting the key characteristics of breast tumor.

Large-scale AI models such as GPT-4 have accelerated the deployment of artificial intelligence across critical domains including law, healthcare, and finance, raising urgent questions about trust and transparency. This study investigates the relationship between explainability and user trust in AI systems through a quantitative experimental design. Using an interactive, web-based loan approval simulation, we compare how different types of explanations, ranging from basic feature importance to interactive counterfactuals influence perceived trust. Results suggest that interactivity enhances both user engagement and confidence, and that the clarity and relevance of explanations are key determinants of trust. These findings contribute empirical evidence to the growing field of human-centered explainable AI, highlighting measurable effects of explainability design on user perception

Machine learning (ML) promises to revolutionize public health through improved surveillance, risk stratification, and resource allocation. However, without systematic attention to algorithmic bias, ML may inadvertently reinforce existing health disparities. We present a systematic literature review of algorithmic bias identification, discussion, and reporting in Dutch public health ML research from 2021 to 2025. To this end, we developed the Risk of Algorithmic Bias Assessment Tool (RABAT) by integrating elements from established frameworks (Cochrane Risk of Bias, PROBAST, Microsoft Responsible AI checklist) and applied it to 35 peer-reviewed studies. Our analysis reveals pervasive gaps: although data sampling and missing data practices are well documented, most studies omit explicit fairness framing, subgroup analyses, and transparent discussion of potential harms. In response, we introduce a four-stage fairness-oriented framework called ACAR (Awareness, Conceptualization, Application, Reporting), with guiding questions derived from our systematic literature review to help researchers address fairness across the ML lifecycle. We conclude with actionable recommendations for public health ML practitioners to consistently consider algorithmic bias and foster transparency, ensuring that algorithmic innovations advance health equity rather than undermine it.

A morally acceptable course of AI development should avoid two dangers: creating unaligned AI systems that pose a threat to humanity and mistreating AI systems that merit moral consideration in their own right. This paper argues these two dangers interact and that if we create AI systems that merit moral consideration, simultaneously avoiding both of these dangers would be extremely challenging. While our argument is straightforward and supported by a wide range of pretheoretical moral judgments, it has far-reaching moral implications for AI development. Although the most obvious way to avoid the tension between alignment and ethical treatment would be to avoid creating AI systems that merit moral consideration, this option may be unrealistic and is perhaps fleeting. So, we conclude by offering some suggestions for other ways of mitigating mistreatment risks associated with alignment.

AI alignment research aims to develop techniques to ensure that AI systems do not cause harm. However, every alignment technique has failure modes, which are conditions in which there is a non-negligible chance that the technique fails to provide safety. As a strategy for risk mitigation, the AI safety community has increasingly adopted a defense-in-depth framework: Conceding that there is no single technique which guarantees safety, defense-in-depth consists in having multiple redundant protections against safety failure, such that safety can be maintained even if some protections fail. However, the success of defense-in-depth depends on how (un)correlated failure modes are across alignment techniques. For example, if all techniques had the exact same failure modes, the defense-in-depth approach would provide no additional protection at all. In this paper, we analyze 7 representative alignment techniques and 7 failure modes to understand the extent to which they overlap. We then discuss our results' implications for understanding the current level of risk and how to prioritize AI alignment research in the future.

This paper proposes a rigorous framework to examine the two-way relationship between artificial intelligence (AI), human cognition, problem-solving, and cultural adaptation across academic and business settings. It addresses a key gap by asking how AI reshapes cognitive processes and organizational norms, and how cultural values and institutional contexts shape AI adoption, trust, and use over time. We employ a three-wave longitudinal design that tracks AI knowledge, perceived competence, trust trajectories, and cultural responses. Participants span academic institutions and diverse firms, enabling contextual comparison. A dynamic sample continuous, intermittent, and wave-specific respondents mirrors real organizational variability and strengthens ecological validity. Methodologically, the study integrates quantitative longitudinal modeling with qualitative thematic analysis to capture temporal, structural, and cultural patterns in AI uptake. We trace AI acculturation through phases of initial resistance, exploratory adoption, and cultural embedding, revealing distinctive trust curves and problem-solving strategies by context: academic environments tend to collaborative, deliberative integration; business environments prioritize performance, speed, and measurable outcomes. Framing adoption as bidirectional challenges deterministic views: AI both reflects and reconfigures norms, decision-making, and cognitive engagement. As the first comparative longitudinal study of its kind, this work advances methodological rigor and offers actionable foundations for human-centred, culturally responsive AI strategies-supporting evidence-based policies, training, and governance that align cognitive performance, organizational goals, and ethical commitments.

Is an LLM telling you different facts than it's telling me? This paper introduces ConsistencyAI, an independent benchmark for measuring the factual consistency of large language models (LLMs) for different personas. ConsistencyAI tests whether, when users of different demographics ask identical questions, the model responds with factually inconsistent answers. Designed without involvement from LLM providers, this benchmark offers impartial evaluation and accountability. In our experiment, we queried 19 LLMs with prompts that requested 5 facts for each of 15 topics. We repeated this query 100 times for each LLM, each time adding prompt context from a different persona selected from a subset of personas modeling the general population. We processed the responses into sentence embeddings, computed cross-persona cosine similarity, and computed the weighted average of cross-persona cosine similarity to calculate factual consistency scores. In 100-persona experiments, scores ranged from 0.9065 to 0.7896, and the mean was 0.8656, which we adopt as a benchmark threshold. xAI's Grok-3 is most consistent, while several lightweight models rank lowest. Consistency varies by topic: the job market is least consistent, G7 world leaders most consistent, and issues like vaccines or the Israeli-Palestinian conflict diverge by provider. These results show that both the provider and the topic shape the factual consistency. We release our code and interactive demo to support reproducible evaluation and encourage persona-invariant prompting strategies.

As large language models (LLMs) continue to advance rapidly, reliable governance tools have become critical. Publicly verifiable watermarking is particularly essential for fostering a trustworthy AI ecosystem. A central challenge persists: balancing text quality against detection robustness. Recent studies have sought to navigate this trade-off by leveraging signals from model output distributions (e.g., token-level entropy); however, their reliance on these model-specific signals presents a significant barrier to public verification, as the detection process requires access to the logits of the underlying model. We introduce STELA, a novel framework that aligns watermark strength with the linguistic degrees of freedom inherent in language. STELA dynamically modulates the signal using part-of-speech (POS) n-gram-modeled linguistic indeterminacy, weakening it in grammatically constrained contexts to preserve quality and strengthening it in contexts with greater linguistic flexibility to enhance detectability. Our detector operates without access to any model logits, thus facilitating publicly verifiable detection. Through extensive experiments on typologically diverse languages-analytic English, isolating Chinese, and agglutinative Korean-we show that STELA surpasses prior methods in detection robustness. Our code is available at https://github.com/Shinwoo-Park/stela_watermark.

In this growing age of data and technology, large black-box models are becoming the norm due to their ability to handle vast amounts of data and learn incredibly complex input-output relationships. The deficiency of these methods, however, is their inability to explain the prediction process, making them untrustworthy and their use precarious in high-stakes situations. SHapley Additive exPlanations (SHAP) analysis is an explainable AI method growing in popularity for its ability to explain model predictions in terms of the original features. For each sample and feature in the data set, we associate a SHAP value that quantifies the contribution of that feature to the prediction of that sample. Clustering these SHAP values can provide insight into the data by grouping samples that not only received the same prediction, but received the same prediction for similar reasons. In doing so, we map the various pathways through which distinct samples arrive at the same prediction. To showcase this methodology, we present a simulated experiment in addition to a case study in Alzheimer's disease using data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. We also present a novel generalization of the waterfall plot for multi-classification.