Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 20 of 24 for “"Trustworthy AI"”.

  1. Engineering data-sharing practices for a fair and trustworthy AI

    … that ML applications are more likely to fail in identifying women than males in hospitals. Recent research has identified the data used to train these models as one of the causes of these issues. The research community has proposed guidelines to detect the dimensions that can generate …

    catalunya Repository record for Engineering data-sharing practices for a fair and trustworthy AI (opens in a new tab)

  2. Towards Trustworthy AI: Investigating Bias and Confidence Alignment in Large Language Models

    … they express when queried about their certainty. This analysis is enriched by employing diverse datasets and prompting techniques aimed at encouraging model introspection, such as structured evaluation scales and the inclusion of answer options. Notably, OpenAI’s GPT-4 emerges as a leading …

    brock Repository record for Towards Trustworthy AI: Investigating Bias and Confidence Alignment in Large Language Models (opens in a new tab)

  3. Reliable and Trustworthy AI for Evidence-based Clinical Decision Support in Cancer Care

    The integration of cutting-edge AI methods with real-world clinical data has moved from being a novelty to a necessity in oncology. However, the deployment of AI faces challenges, including the complexity of reliably modeling longitudinal Electronic Health Records (EHR) characterized by missing …

    mit Repository record for Reliable and Trustworthy AI for Evidence-based Clinical Decision Support in Cancer Care (opens in a new tab)

  4. On Performance and Trustworthiness of AI: from inverse problems to Artificial General Intelligence

    Artificial Intelligence (AI) has emerged as a powerful problem-solving tool, both in the mathematical field of inverse problems and, more recently, in broader applications with the advent of modern chatbots. However, AI systems have repeatedly been shown to be prone to producing hallucinations, …

    cambridge Repository record for On Performance and Trustworthiness of AI: from inverse problems to Artificial General Intelligence (opens in a new tab)

  5. Evaluating Trust in AI-Assisted Bridge Inspection through VR

    The integration of Artificial Intelligence (AI) in collaborative tasks has gained momentum, with particular implications for critical infrastructure maintenance. This study examines the assurance goals of AI—security, explainability, and trustworthiness—within Virtual Reality (VR) environments for …

    vt Repository record for Evaluating Trust in AI-Assisted Bridge Inspection through VR (opens in a new tab)

  6. EFFORTS TOWARD TRUSTWORTHY MACHINE LEARNING: MITIGATING OVERCONFIDENCE, HALLUCINATION, AND MODALITY BIAS

    Trustworthy machine learning is critical for safe deployment of AI systems in high-stakes domains. Despite strong performance, models remain prone to reliability issues such as overconfidence, hallucinations, and modality bias. This thesis addresses these challenges through post-hoc methods and …

    nus Repository record for EFFORTS TOWARD TRUSTWORTHY MACHINE LEARNING: MITIGATING OVERCONFIDENCE, HALLUCINATION, AND MODALITY BIAS (opens in a new tab)

  7. Multiagent Approaches to Enhance Learning and Trust in AI Systems

    … ensuring trust in real-world deployment. Many domains involve multiple adaptive agents interacting under uncertainty and limited information. To be effective, agents must adapt continuously while operating efficiently in large and complex decision spaces. Using frameworks such as extensive form …

    uic

  8. Explainable Neural Claim Verification Using Rationalization

    … which is a significant challenge. Although claim verification techniques exist, they lack proper explainability. Numerical scores such as Attention and Lime and visualization techniques such as saliency heat maps are insufficient because they require specialized knowledge. It is inaccessible …

    vt Repository record for Explainable Neural Claim Verification Using Rationalization (opens in a new tab)

  9. Understanding and Improving Representational Robustness of Machine Learning Models

    … we define as the “robustness” (or generally trustworthy properties) in the induced hidden space of a given network. For a generic representation network, this corresponds to the representation space itself, while for a smoothed model, we will treat the logits of the network as the target …

    mit Repository record for Understanding and Improving Representational Robustness of Machine Learning Models (opens in a new tab)

  10. Machine Learning Methodologies for Beyond 5G and 6G Heterogeneous Networks: Prediction, Automation, and Performance Analysis

    … authentication system. This system utilizes trustworthy AI and template obfuscation to ensure secure and confidential authentication, with excellent performance (ROC up to 0.99) and fast processing (1.47 seconds on average). Finally, a novel Energy Optimized Semantic Loss (EOSL) function is …

    umkc Repository record for Machine Learning Methodologies for Beyond 5G and 6G Heterogeneous Networks: Prediction, Automation, and Performance Analysis (opens in a new tab)

  11. Neurosymbolic Reasoning for Link Prediction in Supply Chain Knowledge Graphs

    … is motivated by recent developments in Supply Chain Management (SCM) and Artificial Intelligence (AI). On one side, as modern supply chains become complex and interconnected with invisible dependencies, we increasingly see disruptions emerging and propagating across the network. This phenomenon, …

    cambridge Repository record for Neurosymbolic Reasoning for Link Prediction in Supply Chain Knowledge Graphs (opens in a new tab)

  12. Understanding and Mitigating Data-Centric Vulnerabilities in Modern AI Systems

    Modern artificial intelligence (AI) systems, trained on vast internet-scale datasets, demonstrate remarkable performance and emergent capabilities. However, this reliance on large datasets that are expensive or difficult to quality-control exposes AI systems to critical vulnerabilities, including …

    vt Repository record for Understanding and Mitigating Data-Centric Vulnerabilities in Modern AI Systems (opens in a new tab)

  13. Trustworthy Reinforcement Learning under Constraints and Perturbations

    … success in sequential decision making across domains such as game playing, autonomous driving, and large-scale resource allocation. However, deploying RL agents in real-world applications requires more than achieving high task performance, since it demands trustworthiness, encompassing safety, …

    auckland-ms Repository record for Trustworthy Reinforcement Learning under Constraints and Perturbations (opens in a new tab)

  14. Robust and Efficient AI-models for Medical Image Reconstruction, Segmentation, and Multimodal Knowledge Distillation

    Artificial intelligence (AI) is transforming the healthcare landscape, offering the promise of earlier diagnoses, more personalized treatments, and improved patient outcomes. However, despite its tremendous potential, deploying AI in real-world clinical settings remains fraught with challenges. …

    unr Repository record for Robust and Efficient AI-models for Medical Image Reconstruction, Segmentation, and Multimodal Knowledge Distillation (opens in a new tab)

  15. SDP-CROWN: Efficient bound propagation for neural network verification with tightness of semidefinite programming

    Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-19 without embargo terms

    uiuc Repository record for SDP-CROWN: Efficient bound propagation for neural network verification with tightness of semidefinite programming (opens in a new tab)

  16. Context-conscious fairness throughout the machine learning lifecycle

    … increasingly used to inform decisions across domains, there has been a proliferation of literature seeking to define “fairness” narrowly as an error to be “fixed” and to quantify it as an algorithm’s deviation from a formalised metric of equality. Dozens of notions of fairness have been proposed, …

    cambridge Repository record for Context-conscious fairness throughout the machine learning lifecycle (opens in a new tab)

  17. GREMLIN: GOES radar estimation via machine learning to inform NWP

    … statistical tools, artificial intelligence (AI) / machine learning (ML) enables new approaches for connecting models and observations. The objective of this research is to develop techniques for assimilating GOES-R Series observations in precipitating scenes for the purpose of improving …

    colostate Repository record for GREMLIN: GOES radar estimation via machine learning to inform NWP (opens in a new tab)

  18. Human factors in the standardization of AI governance: Improving the design of risk management standards for ethical AI

    Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-19 without embargo terms

    uiuc Repository record for Human factors in the standardization of AI governance: Improving the design of risk management standards for ethical AI (opens in a new tab)

  19. Trustworthy Soft Sensing in Water Supply Systems using Deep Learning

    … conditions, calibration drift, high maintenance costs, and degrading. Researchers have turned to advanced computational methods, including mathematical modeling, statistical analysis, and machine learning, to overcome these limitations. Deep learning techniques have shown promise in …

    vt Repository record for Trustworthy Soft Sensing in Water Supply Systems using Deep Learning (opens in a new tab)

  20. Human-centric trustworthy foundation model reasoning

    … convey information effectively. Advancements in AI have given rise to language models (LMs) being increasingly adopted in assisting information understanding and communication for different task settings. However, the potential that LMs can serve in supporting human communication is still …

    uiuc Repository record for Human-centric trustworthy foundation model reasoning (opens in a new tab)

Page 1 of 2