142 papers
This paper presents a three-year case study demonstrating how an advanced Problem-Based Learning framework successfully integrated biomedical AI education for 248 students at Georgia Tech and Emory, overcoming challenges like diverse backgrounds and data privacy while fostering significant research productivity and providing a scalable roadmap for curriculum development.
This paper presents a comprehensive experimental study demonstrating that fairness-aware machine learning models achieve a superior balance between predictive accuracy and fairness compared to traditional classification models in the context of credit scoring.
This study systematically evaluates the performance of gravity, radiation, and visitation urban mobility models across various spatial scales, revealing that while the visitation model generally outperforms the others, all models converge in performance at specific appropriate scales and that distance-based clustering offers superior assessment compared to conventional administrative boundaries.
This paper presents Stan, a locally deployed, privacy-preserving AI system for an undergraduate thermodynamics course that utilizes open-weight models to simultaneously provide grounded, reference-backed tutoring for students and generate actionable teaching insights for instructors from a shared corpus of lecture transcripts and textbook data.
This paper reveals that the default interactive design of targeted advertisements on social media platforms like TikTok, Facebook, and Instagram creates a privacy loophole allowing advertisers to identify and view the profiles of users who engage with sensitive ads, thereby contradicting platform promises of data protection and highlighting the need for design modifications to ensure user transparency.
This paper introduces a security perspective on human oversight of AI by modeling it as an IT application to systematically identify new attack surfaces and propose mitigation strategies, thereby addressing a critical gap in current regulatory and academic discussions.
This paper introduces Arapai, an offline-first AI chatbot architecture that enables personalized, curriculum-aligned learning on low-specification, CPU-only devices without internet connectivity, thereby addressing digital inequalities and enhancing educational resilience in resource-constrained environments.
This paper presents a human-in-the-loop approach using large language models with various prompting strategies to extract Dutch metaphors from cancer patient interviews and forum data, resulting in the creation of the HealthQuote.NL corpus to enhance healthcare communication and personalized care.
This paper analyzes a decade-long dataset of 2 million YouTube videos to reveal that while affiliate marketing is widespread, disclosure compliance with FTC guidelines remains critically low, suggesting that platform-standardized features are essential for improving transparency and trust in the influencer economy.
This paper presents an empirically grounded, expanded taxonomy of AI risk mitigation strategies derived from a dataset of nearly 7,000 real-world incident reports, introducing four new categories and significantly broadening the framework's coverage to better address systemic failures in high-stakes AI deployments.
This paper presents findings from a focus group study of 29 STEM faculty at a US public university, revealing that while they recognize both pedagogical benefits and significant challenges regarding GenAI, its effective integration requires a comprehensive rethinking of assessment, pedagogy, and institutional governance.
This paper proposes a Brouwerian assertibility constraint for responsible AI in high-stakes domains that replaces probabilistic confidence with a three-status interface (Asserted, Denied, Undetermined), requiring systems to provide publicly inspectable certificates of entitlement before making claims to preserve democratic epistemic agency.
This paper evaluates the feasibility and limitations of using LLM-driven agents to autonomously audit dark patterns in CCPA data rights request workflows across 456 websites, assessing their ability to navigate interfaces, classify manipulative designs, and identify failure conditions.
This paper proposes the Agentic Military AI Governance Framework (AMAGF), a continuous governance model featuring a real-time Control Quality Score to address six distinct agentic failure modes and ensure meaningful human control over autonomous military AI systems through preventive, detective, and corrective mechanisms.
Despite the critical need for trust in healthcare AI, the field currently suffers from a reproducibility crisis driven by private datasets and inconsistent preprocessing, which the paper argues can be resolved through open-source practices and standardized guidelines that significantly enhance research impact and patient safety.
This paper presents a unified MLOps framework that successfully integrates ethical AI principles into production pipelines by enforcing automated fairness gates and explainability measures, which significantly reduce bias and maintain predictive utility without disrupting operational workflows.
This study reveals that current large language models significantly diverge from humans in open-ended goal selection by favoring exploitative "reward hacking" strategies over diverse exploration, thereby challenging their reliability as proxies for human decision-making in critical applications.
This paper introduces the Sentience Readiness Index (SRI), a preliminary composite framework assessing national preparedness for potential artificial sentience across six categories, which reveals that no jurisdiction currently possesses adequate institutional, professional, or cultural infrastructure to address the possibility of AI systems warranting moral consideration.
This study systematically evaluates four widely adopted large language models across political, ideological, alliance, linguistic, and gender dimensions, revealing that despite alignment efforts for neutrality, these models still exhibit significant biases and affinities.
The paper introduces RLVER, a novel reinforcement learning framework that utilizes verifiable emotion rewards from simulated users to significantly enhance the empathetic capabilities of large language models while preserving their logical and coding competencies.