Digital Commons Network^™

Adapting Large Language Models For Parameter-Efficient Log Anomaly Detection, Ying Fu Lim, Jiawen Zhu, Guansong Pang

Research Collection School Of Computing and Information Systems

Log Anomaly Detection (LAD) seeks to identify atypical patterns in log data that are crucial to assessing the security and condition of systems. Although Large Language Models (LLMs) have shown tremendous success in various fields, the use of LLMs in enabling the detection of log anomalies is largely unexplored. This work aims to fill this gap. Due to the prohibitive costs involved in fully fine-tuning LLMs,we explore the use of parameter-efficient fine-tuning techniques (PEFTs) for adapting LLMs to LAD.To have an in-depth exploration of the potential of LLM-driven LAD, we present a comprehensive investigation of leveraging two of the most …

Optical Character Recognition For Early Handwriting Legibility Assessment, Franceli L. Cibrian, Kayla Anderson, Yingying 'Yuki' Chen, Lauren Min, Lizbeth Escobedo

Engineering Faculty Articles and Research

Monitoring children’s handwriting, such as avoiding writing assignments, displaying uneven letter formation, or showing slow writing speed, can help identify developmental and academic issues early. Poor handwriting affects up to 34% of children, leading to academic and self-esteem challenges. Handwriting assessments, typically conducted by teachers, are often delayed due to workload and could be subjective and inconsistent. This paper explores the potential of Optical Character Recognition (OCR) technology to augment and ease handwriting assessments. Based on an evaluation of 10 OCR algorithms using 33 handwriting samples assessed by two experts, the research indicates that Pen to Print and Google are …

Collaborative Tree Search For Enhancing Embodied Multi-Agent Collaboration, Lizheng Zu, Lin Lin, Song Fu, Na Zhao, Pan Zhou

Research Collection School Of Computing and Information Systems

Embodied agents based on large language models (LLMs) face significant challenges in collaborative tasks, requiring effective communication and reasonable division of labor to ensure efficient and correct task completion. Previous approaches with simple communication patterns carry erroneous or incoherent agent actions, which can lead to additional risks. To address these problems, we propose Cooperative Tree Search (CoTS), a framework designed to significantly improve collaborative planning and task execution efficiency among embodied agents. CoTS guides multi-agents to discuss long-term strategic plans within a modified Monte Carlo tree, searching along LLMdriven reward functions to provide a more thoughtful and promising approach to …

A Knowledge Enhanced Large Language Model For Bug Localization, Yue Li, Bohan Liu, Ting Zhang, Zhiqi Wang, David Lo, Lanxin Yang, Jun Lyu, He Zhang

Research Collection School Of Computing and Information Systems

A significant number of bug reports are generated every day as software systems continue to develop. Large Language Models (LLMs) have been used to correlate bug reports with source code to locate bugs automatically. The existing research has shown that LLMs are effective for bug localization and can increase software development efficiency. However, these studies still have two limitations. First, these models fail to capture context information about bug reports and source code. Second, these models are unable to understand the domain-specific expertise inherent to particular projects, such as version information in projects that are composed of alphanumeric characters without …

Efficient And Green Large Language Models For Software Engineering: Literature Review, Vision, And The Road Ahead, Jieke Shi, Zhou Yang, David Lo

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) have recently shown remarkable capabilities in various software engineering tasks, spurring the rapid growth of the Large Language Models for Software Engineering (LLM4SE) area. However, limited attention has been paid to developing efficient LLM4SE techniques that demand minimal computational cost, time, and memory resources, as well as green LLM4SE solutions that reduce energy consumption, water usage, and carbon emissions. This article aims to redirect the focus of the research community toward the efficiency and greenness of LLM4SE, while also sharing potential research directions to achieve this goal. It commences with a brief overview of the significance …

A Neutrosophic And Q-Rung Orthopair Fuzzy Sets Approach For Desertification Susceptibility Mapping: A Case Study In Matrouh, Egypt, Nabil M. Abdelaziz, Khalid A. Eldrandaly, Amira M. Fawzy, Gehan A. Fouad, Safa Al-Saeed

Neutrosophic Systems with Applications

This study introduces an innovative approach to desertification susceptibility mapping by integrating q-rung orthopair fuzzy sets (Q-ROFS) with a neutrosophic environment. Conducted in Matrouh, Egypt, the research quantifies desertification risk through advanced modeling techniques that address uncertainty and non-linearity in environmental data. The Q-ROFS framework enhances risk prediction by capturing complex relationships among desertification indicators. Neutrosophic logic, meanwhile, effectively addresses imprecision and ambiguity. The resulting susceptibility map clearly distinguishes between vulnerable and non-vulnerable regions, offering valuable guidance for policymakers and planners. The analysis revealed that approximately 79.98% of the study area falls under moderate susceptibility, 14.27% under high susceptibility, and …

A Critical Evaluation Of The Criticisms Against Neutrosophic Statistical Methods, Muhammad Aslam, Abdulrahman Alaita, Florentin Smarandache

Neutrosophic Systems with Applications

Neutrosophic statistical analysis has gained attention for incorporating the degree of indeterminacy when analyzing imprecise and interval data under uncertainty–-an aspect often overlooked by classical statistics, fuzzy statistical analysis, and interval statistics. Recently, critical discussions have emerged regarding the use and applications of neutrosophic statistics, with some questioning its usefulness and validity. In this paper, we present a critical assessment of the existing literature, focusing on areas where misunderstandings and misinterpretations of neutrosophic statistical methods have occurred. We also examine flawed comparisons made between the results of neutrosophic statistics and interval statistics. Furthermore, substantial issues have been identified in the …

Contract Quality Feature Extraction Using Llm, Aaron C. Washington

Theses and Dissertations

This study explored the potential insights generated from linguistic complexity measurements and large language model (LLM) based assessments on the quality of contract documents. By combining structured True/False prompts with log-probability analysis and ambiguity scoring, the study introduced novel contract-quality assessment methods. Results support a feature-driven approach to contract evaluation, one that offers automated, scalable insights for triaging risk and improving drafting practices. These assessment methods contribute to the growing field of legal natural language processing by offering modular tools for effective contract analysis.

Meta-Learning Hyperparameters For Foundation Model Adaptation In Remote-Sensing Imagery, Zichen Tian, Yaoyao Liu, Qianru Sun

Research Collection School Of Computing and Information Systems

Training large foundation models of remote-sensing (RS) images is almost impossible due to the limited and long-tailed data problems. Fine-tuning natural image pre-trained models on RS images is a straightforward solution. To reduce computational costs and improve performance on tail classes, existing methods apply parameter-efficient fine-tuning (PEFT) techniques, such as LoRA and AdaptFormer. However, we observe that fixed hyperparameters -- such as intra-layer positions, layer depth, and scaling factors, can considerably hinder PEFT performance, as fine-tuning on RS images proves highly sensitive to these settings. To address this, we propose MetaPEFT, a method incorporating adaptive scalers that dynamically adjust module …

Hd-Epic: A Highly-Detailed Egocentric Video Dataset, Toby Perrett, Ahmad Darkhalil, Saptarshi Sinha, Omar Emara, Sam Pollard, Kranti Kumar Parida, Kaiting Liu, Prajwal Gatti, Siddhant Bansal, Kevin Flanagan, Jacob Chalk, Zhifan Zhu, Rhodri Guerrier, Fahd Abdelazim, Bin Zhu, Davide Moltisanti, Michael Wray, Hazel Doughty, Dima Damen

Research Collection School Of Computing and Information Systems

We present a validation dataset of newly-collected kitchenbased egocentric videos, manually annotated with highly detailed and interconnected ground-truth labels covering: recipe steps, fine-grained actions, ingredients with nutritional values, moving objects, and audio annotations. Importantly, all annotations are grounded in 3D through digital twinning of the scene, fixtures, object locations, and primed with gaze. Footage is collected from unscripted recordings in diverse home environments, making HDEPIC the first dataset collected in-the-wild but with detailed annotations matching those in controlled lab environments. We show the potential of our highly-detailed annotations through a challenging VQA benchmark of 26K questions assessing the capability to …

Large Language Models For Logical Fallacy Detection, Nicole Anne Hui-Ying Teo, Donghao Huang, Erik Cambria, Zhaoxia Wang

Research Collection School Of Computing and Information Systems

Identifying logical fallacies is essential for maintaining log-ical reasoning and reducing false information in a variety of domains, such as the media, law, and education. We present an extensive study on the use of large language models (LLMs) for logical fallacy detection and provide a comparative overview of model performance across various fallacy classes. We evaluate the logical fallacy detection capabilities of multiple state-of-the-art models (LLaMA, Qwen, Gemma, Phi) utilizing accuracy, precision, recall, and F1-score as assessment measures. Accord-ing to our findings, our models do well on simple fallacies like “circular reasoning,” but they have trouble with more interpretive reasoning …

Specialization Or Diversification? Creators’ Strategies On User-Generated Content Platforms, Ziwei Ye

Theses and Dissertations in Business Administration

Recent advancements in digital platforms have reshaped content creation and distribution. User-generated content (UGC), created and shared by internet users, is transforming entertainment, communication, and information sharing. The rise of UGC has fueled the growth of the "creator economy"—an ecosystem of creators, users, and advertisers facilitated by platforms such as YouTube and TikTok. While prior research has primarily explored how UGC platforms incentivize content quantity and quality, this study advances the literature by examining how creators' content strategies influence consumer attention and how platform mechanisms shape this relationship, offering new insights into the interplay between creator behavior and platform design. …

Adversarial Robustness In Advanced Machine Learning Models Integrating Graph Neural Networks And Large Language Models, Mahmoud Nazzal

Dissertations

Artificial intelligence (AI) has achieved remarkable performances across various domains. In most real-world applications, data often takes relational forms, such as graphs and networks, or sequential forms, such as text and time series. As AI evolves, specialized models have emerged to handle these structures; Graph Neural Networks (GNNs) for relational mining and Large Language Models (LLMs) for sequential understanding. Despite their success, these models face challenges in security, robustness, and interpretability. GNNs excel in relational reasoning but are vulnerable to adversarial manipulation and lack interpretability, while LLMs are strong in linguistic reasoning and generalization yet struggle with relational data and …

Fact-Checking As A Multi-Step Process: From Ambiguity Resolution To Claim Validation, Wenbo Wang

Dissertations

The spread of misinformation and disinformation has become a major concern, particularly with the rise of social media as a primary source of information for many people. Fact-checking—the process of verifying claims against credible evidence—has emerged as a critical safeguard against misinformation. Yet, the task is fraught with challenges: claims are often ambiguous, context-dependent, or composed of multiple intertwined assertions, while automated systems struggle to replicate the nuanced reasoning of human experts. This dissertation addresses these challenges by reimagining fact-checking as a multi-step, knowledge-guided process that systematically resolves ambiguity, decomposes complexity, and validates claims through structured reasoning. Additionally, the proposed …

From Neural Networks To Large Language Models: Innovations In Financial Ai, Mathematical Reasoning, And Structured Data Representation, Junyi Ye

Dissertations

This dissertation explores the evolution and application of artificial intelligence techniques across three critical domains: financial modeling, mathematical reasoning, and structured data analysis. The dissertation presents seven research projects that chart a progression from specialized neural architectures to sophisticated large language models (LLMs), contributing novel methodologies and frameworks at each stage.

In the financial domain, the research first introduces TS-Mixer, a MLP-based architecture for time-series forecasting that captures both feature relationships and temporal dependencies through a simple yet effective design, outperforming more complex models in S&P500 index prediction. The dissertation then presents DySTAGE, a dynamic graph representation learning framework that …

Quantum-Enhanced Training Of Large Language Models: A Hybrid Approach, Nan Wu, Fangmin Song, Xiangdong Li

Publications and Research

The training of large language models (LLMs) presents significant computational challenges, particularly regarding efficient convergence. This paper presents a hybrid quantum-classical framework designed to address the significant computational challenges associated with training large language models (LLMs). By integrating quantum computing principles superposition, entanglement, and tunneling with classical deep learning methods, we propose an approach to accelerate convergence, enhance optimization efficiency, and improve model generalization. Specifically, quantum feature mapping is employed to project classical data into high-dimensional Hilbert spaces, facilitating more expressive data representations. Quantum-assisted optimization algorithms, such as Quantum Approximate Optimization Algorithm (QAOA) and Variational Quantum Eigensolver (VQE), efficiently navigate …

Who Should Take Responsibility For Artificial Intelligence Actions And Outcomes? Perception Of Auditors As Users Of Ai Systems, Hanh Hoang Le

Doctoral Dissertations

As artificial intelligence (AI) systems become increasingly embedded in auditing processes, questions arise regarding how professional auditors perceive and allocate responsibility for AI-assisted decisions. This study investigates the effects of AI explainability and auditors’ perceived autonomy on perceived responsibility in the context of audit decision-making. Drawing on theories of moral responsibility and professional judgment, the study employs a 2x2 experimental design using hypothetical audit scenarios to manipulate levels of AI explainability and auditors’ autonomy. Hierarchical regression analysis reveals that perceived autonomy statistically significantly increases auditors’ perception of responsibility for AI-assisted decisionmaking, whereas AI explainability is not a significant predictor. Additionally, …

Towards Multi-Modal Multi-Document Understanding Capabilities In Foundation Models, Chuhan Li

Computer Science Theses

Contemporary foundation models are predominantly evaluated on isolated documentor image-understanding tasks, thereby overlooking the inherent multimodal multi-document reasoning that characterizes scientific inquiry. To bridge this gap, M3SCIQA is introduced, aMulti-Modal,Multi-document Scientific Question Answering benchmark crafted to test foundation models in practical scientific research settings. A comprehensive evaluation of 18 leading foundation models shows a substantial performance gap between models and human experts. Detailed error analysis reveals persistent deficiencies in both scientific visual reasoning tasks and long-range retrieval. Addressing the former, SPACECUE offers a concise yet effective visual prompting that overlays grid coordinates and Semantic-SAM masks …

Zeroizing Trust In A Naïve Federated Zero Trust Environment, Keith E. Strandell

Theses and Dissertations

The position of the United States on the global stage is predicated on information dominance and the ability to project power through cooperative engagements with mission partners in both wartime and peacetime. Recent cyber-attacks highlighted the need for a more robust cybersecurity posture. As the United States progresses toward the adoption of Zero Trust, it is incumbent on the Department of Defense to assess the impact to the ability to share data across strategic partnerships while securing the data of both the United States and its partners. This paper proposes research into ensuring an environment rooted in Zero Trust and …

Developments On Abbreviations Towards Machine Reading Comprehension, Sing Choi

UNLV Theses, Dissertations, Professional Papers, and Capstones

Machine reading comprehension is a critical step in development of applications that require the semantic understanding of human speech-to-text driven work. Many devices such as smart home appliances like the Amazon Echo Dot, Google Home, or smart assistants like Apple Siri or Microsoft Cortana are examples of these applications. The comprehension task involves a deeper understanding and recognition of named entities such as person names, locations, medicals codes, quantities, abbreviations, and acronyms in speech or text data. In this dissertation, we explore and extend the different approaches and techniques in modern research that tackles the problem of recognition and definition …

Memory-Augmented Llm Agent For Predicting Locomotion Modes In Construction Activities, Ehsan Ahmadi

LSU Doctoral Dissertations

The construction industry faces significant challenges, including labor shortages, high physical demands, and safety risks, necessitating advanced assistive technologies like exoskeletons to enhance worker efficiency and reduce injuries. However, effective exoskeleton control in dynamic construction environments requires accurate locomotion prediction, a task complicated by the diversity of activities and reliance on supervised learning methods that struggle to generalize. This study investigates a multimodal approach to locomotion prediction, leveraging speech commands and visual data from smart glasses to enable adaptive and safe human-exoskeleton interaction. The research unfolds in two stages: the first develops a framework to evaluate the zero-shot capability and …

The Evolution And Impact Of Blog Analysis Tools: A Study Of Blogtracker's Comprehensive Approach To Digital Discourse Analysis, Oyindamola Koleoso

Theses and Dissertations

This study presents BlogTracker, a comprehensive web-based platform designed to address the growing complexities of analyzing the modern blogosphere. We detail BlogTracker's evolution from earlier blog analysis tools, highlighting its innovative integration of features including real-time data collection, advanced content analysis, sentiment analysis, influence tracking, and narrative analysis. At the core of our contribution is a robust content extraction system that achieves 91.33% accuracy across diverse blog formats, providing a reliable foundation for all analytical functions. This extraction system effectively distinguishes between primary content and peripheral elements, ensuring high-quality inputs for downstream analysis regardless of source blog structure. The platform's …

Modeling Cross-Platform Narrative Templates: A Temporal Knowledge Graph Approach, Ridwan Amure

Theses and Dissertations

Over the past decade, social media platforms have rapidly evolved in scale, functionality, and user engagement, encouraging individuals to maintain active presences across multiple networks. This complex, interconnected ecosystem has also enabled information actors to exploit cross-platform dynamics to amplify the reach of their content and strategically target diverse audiences. Recognizing the persistence and adaptability of such actors, this research emphasizes the need for robust models that can effectively capture and analyze cross-platform narrative diffusion. To this end, we propose a framework that utilizes temporal knowledge graphs to model the evolution and relationships among narratives across platforms. We extract temporal …

Beyond Boundaries: A Comprehensive Survey Of Transferable Attacks On Ai Systems, Guangjing Wang, Ce Zhou, Yuanda Wang, Bocheng Chen, Hanqing Guo, Qiben Yan

Computer Science Faculty Research & Creative Works

As Artificial Intelligence (AI) systems increasingly underpin critical applications, from autonomous vehicles to biometric authentication, their vulnerability to transferable attacks presents a growing concern. These attacks, designed to generalize across instances, domains, models, tasks, modalities, or even hardware platforms, pose severe risks to security, privacy, and system integrity. This survey delivers the first comprehensive review of transferable attacks across seven major categories, including evasion, backdoor, data poisoning, model stealing, model inversion, membership inference, and side-channel attacks. We introduce a unified six-dimensional taxonomy: cross-instance, cross-domain, cross-modality, cross-model, cross-task, and cross-hardware, which systematically captures the diverse transfer pathways of adversarial strategies. Through …

Harnessing Llms To Detect Hate Speech, Weibin Cai

Theses - ALL

Hate is a sentiment, while hate speech refers to the expression of hate in a form that targets and attacks specific groups, such as race, religion, or gender. With the rise of the internet and social media, hate speech has spread rapidly, gaining wide exposure and posing threats to individual well-being, the profits of major tech companies, and social stability. As a result, both industry and academia have turned their attention to the study of hate speech. One of the most active areas is hate speech detection, which involves training models to predict whether a given piece of content is …

Optimized Student Grouping For Enhanced Classroom Performance, Kathryn E. Reardon

Honors Theses

Effective grouping methods enhance classroom collaboration and allow for a student-centered teaching approach; however, traditional grouping methods are time-consuming, subjective, and can create inconsistent group dynamics. This project addresses these challenges by employing a data-driven approach to optimize student groups based on academic performance, behavior, attendance, language barriers, and teacher preferences. The minimum viable product is a web application with an algorithm-driven system to group students and a database storage for group results. During the initiation phase, a problem was defined with a proposed solution. During the planning phase, potential design choices and grouping methods were researched and assessed. During …

Effective And Efficient Graph Foundation Model, Lecheng Kong

McKelvey School of Engineering Graduate Student Theses & Dissertations

Graph data has emerged as a central component in numerous real-world applications, spanning recommender systems, drug discovery, social networking, and traffic forecasting. While traditional and modern graph learning techniques—ranging from graph kernels to Graph Neural Networks (GNNs) and graph transformers—have achieved significant success, their task-specific nature and reliance on supervised learning limit their adaptability to new, unseen tasks. This rigidity becomes especially problematic in dynamic environments where retraining for every new task is costly and often infeasible. Inspired by the transformative impact of foundation models in natural language processing, this thesis explores the feasibility of developing a graph foundation model—a …

Towards Secure And Privacy-Preserving Machine Learning Systems, Han Liu

McKelvey School of Engineering Graduate Student Theses & Dissertations

In recent years, machine learning (ML) has advanced at an unprecedented pace, driving the widespread adoption of increasingly sophisticated models across a broad range of real-world applications, including healthcare, finance, autonomous systems, and critical infrastructure. While these models have delivered remarkable benefits and transformed numerous industries, they remain inherently vulnerable to a variety of security and privacy threats. Given their growing role in safety-critical domains, ensuring their security and privacy has become imperative. Systematically addressing these vulnerabilities requires comprehensive adversarial analyses to uncover weaknesses and inform the design of robust defenses. This dissertation systematically investigates ML vulnerabilities in adversarial settings …

Voice Interaction With Conversational Ai Could Facilitate Thoughtful Reflection And Substantive Revision In Writing, Jiho Kim, Philippe Laban, Xiang 'Anthony' Chen, Kenneth C. Arnold

University Faculty Publications and Creative Works

Writing well requires not only expressing ideas but also refining them through revision, a process facilitated by reflection. Prior research suggests that feedback delivered through dialogues, such as those in writing center tutoring sessions, can help writers reflect more thoughtfully on their work compared to static feedback. Recent advancements in multi-modal large language models (LLMs) now offer new possibilities for supporting interactive and expressive voice-based reflection in writing. In particular, we propose that LLM-generated static feedback can be repurposed as conversation starters, allowing writers to seek clarification, request examples, and ask follow-up questions, thereby fostering deeper reflection on their writing. …

Optimizing Small Ai Models For Biomedical Tasks Through Efficient Knowledge Transfer From Large Domain Models, Girish Sundaram

Theses and Dissertations

The PICO (Population, Intervention, Comparison, Outcome) framework is a widely adopted methodology for structuring clinical research questions and extracting relevant information from unstructured medical texts. However, traditional approaches for PICO classification demand computationally expensive domain-specific language models, such as BioBERT and ClinicalBERT, which require extensive training and large annotated datasets. This dissertation introduces Distilled Rapid Embedding Transfer (DRET), a novel knowledge transfer method designed to enable resource-constrained domain adaptation. DRET aims to efficiently transfer biomedical domain knowledge from large, specialized models to a compact, general-purpose model, DistilBERT, thereby enhancing its ability to perform domain-specific tasks without access to the original …