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 19 of 19 for “"AI Fairness"”.
-
Topics on AI Fairness Preferences in Kidney Transplantation
… incorporates artificial intelligence (AI) decision-support systems which exhibit social discrimination due to biases inherited from training data. Although researchers have proposed various group-based fairness notions to assess biases in AI, it remains uncertain which criterion is most …
-
Three ethical dimensions of AI: Fairness in social recommenders, bias detection in LLMs, and privacy in NLP
… of responsible Artificial Intelligence (AI): fairness in social recommender systems, demographic bias in large language models (LLMs), and privacy-preserving techniques for Natural Language Processing (NLP). Though these problems differ in technical scope and application domain, they …
-
The Impact of AI-based Recommendation System Discrimination on Performance: The Role of Transparency
Modern artificial intelligence (AI) systems are increasingly embedded in decision-making contexts, yet their outputs are not always fair or unbiased. This study investigates how discriminatory AI predictions—specifically discriminatory housing price estimates—impact human decision-making, and how …
-
Exploring Representational Harms of Generative AI Systems upon Historically Marginalized Populations often Overlooked in Fairness Research
… finds itself firmly in the midst of a Generative AI (GAI) summer -- a period of abundant investment, research, and interest around the development of Artificial Intelligence tools. Since the public release of OpenAI's ChatGPT, GAI tools have seen widespread adoption across the public and private …
-
Fairness of Artificial Intelligence in Predicting Recidivism Risk and Beyond
This thesis designs, evaluates, and deploys fairness-aware artificial intelligence (AI) systems for recidivism prediction and other high-stakes domains. It addresses persistent gaps in the literature by integrating fairness interventions across the AI lifecycle, improving fairness–accuracy …
-
Does Artificial Intelligence Bias Exist in Mortgage Underwriting Software? Investigating Bias, Regional Disparities, and Fair AI Models
… emulated Zou and Khern's (2022) analysis of AI Bias in Mortgage Applications. They used the Home Mortgage Disclosure Act (HMDA) dataset from the Federal Financial Institution Examination Council's (FFEIC) website to review mortgage loan data from 2019 to determine if there was bias in the AI …
-
Building Trustable Methods for Group Recommendations: Advancing Fairness and Robustness Across Domains
On the internet, where the number of available choices for information is exponentially growing, there is a need to prioritize and deliver relevant results to users efficiently, on demand. Recommendation systems (RSs) address that need by searching through and filtering large amounts of dynamically …
-
Knowledge Augmentation in Language Models to Overcome Domain Adaptation and Scarce Data Challenges in Clinical Domain
… produces” and “the scarcity of sufficient training data to train language models,” in the healthcare domain have multifold increased the need for intelligent tools and techniques to process, interpret and extract different types of knowledge from the data. My research goal in this thesis is …
-
Mitigating Racial Biases in Toxic Language Detection
… research has demonstrated how racial biases against users who write African American English exists in popular toxic language datasets. While previous work has focused on a single fairness criteria, we propose to use additional descriptive fairness metrics to better understand the source of …
-
Personalized Algorithmic Recourse: Towards a human-centric approach for algorithmic contestability
… systems in high-stakes decision-making domains, such as lending, employment, and legal proceedings, has raised significant concerns about fairness, transparency, and accountability. High-profile cases, such as the racially biased COMPAS algorithm, highlight the potential societal risks of …
-
Fairness and Ethical Analysis of Classification Models based on Facial Recognition
Facial recognition is a sub-field of AI that has seen tremendous growth over the last decade both in research and commercial applications. However, there has been growing criticism from scholars in various disciplines and media on the potential harms and biases that can be present in facial …
-
Data-driven Algorithms for Critical Detection Problems: From Healthcare to Cybersecurity Defenses
… defenses often rely on black-box models trained on unverified traces, providing limited interpretability. To address the scarcity of reliably labeled training data, we experimentally profile runtime ransomware behaviors of real-world samples and identify core patterns, enabling explainable …
-
The Efficacy of Ethical Data: An Analytical Study by
… or equitable representation. This study aims to compare analytics outcomes (accuracy, bias, fairness, and explainability) between ethically sourced and unethically sourced datasets. Using CRISP-DM methodology, the study will develop matched classification models on both dataset types, …
-
A(I) DESIGN STUDY:: A sociotechnical, card-based fairness tool for ADM-development
… design probe for guiding the embeddedness of fairness in Algorithmic Decision-Making Systems (ADM’s) is created on literature groundings, envisioning a sociotechnical approach. The motive is originated in the practitioners’ call for guidance, in the shape of light-weight, integrable tools …
-
Addressing Human-centered Artificial Intelligence: Fair Data Generation and Classification and Analyzing Algorithmic Curation in Social Media
… impact of artificial intelligence, the topic of fairness in AI has received increasing attention. Artificial intelligence is observed to have caused unanticipated negative consequences. In this dissertation, we address two critical aspects regarding human-centered artificial intelligence (HCAI), …
-
Advancing Responsible AI: Disparity Mitigation Strategies for Human-Centered AI Systems
… improve efficiency and predictive accuracy in domains such as healthcare, finance, and criminal justice, biases inherited from training data can potentially lead to unintended disparities. Growing awareness of these biases has raised concerns within the human-centered AI and responsible AI …
-
Large Language Models: Towards Safety, Robustness, and Understanding
… across a wide range of tasks in the text domain. In order for large language models based on this architecture to be suitable for widespread usage, it is critical to ensure they are not abused for malicious purposes, that they are robust against adversarial attack, and that the behaviour of …