Our projects
Uncertainty Quantification in Large Language Models Through Convex Hull Analysis
Uncertainty quantification approaches have been more critical in large language models (LLMs), particularly high-risk applications requiring reliable outputs. However, traditional methods for uncertainty quantification, such as probabilistic models and ensemble techniques, face challenges when applied to the complex and high-dimensional nature of LLM-generated outputs. This study proposes a novel geometric approach to uncertainty quantification using convex hull analysis. The proposed method leverages the spatial properties of response embeddings to measure the dispersion and variability of model outputs. The prompts are categorized into three types, i.e., ‘easy’, ‘moderate’, and ‘confusing’, to generate multiple responses using different LLMs at varying temperature settings. The responses are transformed into high-dimensional embeddings via a BERT model and subsequently projected into a two-dimensional space using Principal Component Analysis (PCA). The Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm is utilized to cluster the embeddings and compute the convex hull for each selected cluster. The experimental results indicate that the uncertainty of the model for LLMs depends on the prompt complexity, the model, and the temperature setting.
A Benchmark Framework for Data Visualization and Explainable AI (XAI)
This research introduces a benchmark framework, called EDUMX, designed for machine learning (ML)- based forecasting and XAI tasks, leveraging the Streamlit open-source Python library. The framework oQers a comprehensive suite of functionalities, including data loading, feature selection, relationship analysis, data preprocessing, model selection, metric evaluation, training, and real-time monitoring. Users can easily upload data in diverse formats, explore relationships between variables, preprocess data using various techniques, and assess the performance of the ML model using customizable metrics. With its user-friendly interface, this framework oQers invaluable insights for forecasting tasks in various domains, catering to the evolving needs of predictive analytics. EDUMX is available for all to use. Please contact mkuzlu@odu.edu if you would like the details to access this tool.
A Streamlit-based Artificial Intelligence Trust Platform for Next-Generation Wireless Networks
With the rapid development and integration of artificial intelligence (AI) methods in next-generation networks (NextG), AI algorithms have provided significant advantages for NextG in terms of frequency spectrum usage, bandwidth, latency, and security. A key feature of NextG is the integration of AI, i.e., self-learning architecture based on self-supervised algorithms, to improve the performance of the network. A secure AI-powered structure is also expected to protect NextG networks against cyber-attacks. However, AI itself may be attacked, i.e., model poisoning targeted by attackers, and it results in cybersecurity violations. This paper proposes an AI trust platform using Streamlit for NextG networks that allows researchers to evaluate, defend, certify, and verify their AI models and applications against adver
