Digital Commons Network^™

Efficient Integration Of External Knowledge To Llm-Based World Models Via Retrieval-Augmented Generation And Reinforcement Learning, Chang Yang, Xinrun Wang, Qinggang Zhang, Qi Jiang, Xiao Huang

Research Collection School Of Computing and Information Systems

World models achieve remarkable success in predicting future states and planning in complex environments and Large Language Models (LLMs) serve as promising foundation to build general world models. However, their performances are usually constrained by the limited external knowledge to specific environments. Existing research attempts to enhance LLM-based world models through prompting or fine-tuning approaches, which are either requiring human knowledge or computationally extensive. Therefore, we introduce Retrieval-Augmented World Models (RAWM), a novel framework that leverages retrieval-augmented generation to efficiently integrate the external knowledge to LLM-based world models. Our main contributions are threefold: (i) We introduce a memory system and …

One Planner To Guide Them All! Learning Adaptive Conversational Planners For Goal-Oriented Dialogues, Huy Dao, Lizi Liao

Research Collection School Of Computing and Information Systems

Goal-oriented dialogues, such as recommendation and negotiation, often require balancing multiple, conflicting objectives. Existing methods typically involve training separate models for specific combinations of objectives, leading to computational and scalability issues. In this work, we aim to develop a new dialogue policy method that can adapt to varying objective preferences at inference time without retraining. This raises several challenges in terms of both (1) optimization strategy and (2) knowledge utilization. To address these, we propose a novel learning framework, Preference Adaptive Dialogue Policy Planner (PADPP), for multi-objective goal-oriented dialogues. Specifically, to tackle the former, we introduce a novel policy optimization …

Gerunds In Irish Sign Language: An Exploratory Analysis, Zaid Mohammed

Doctoral

In sign languages (SLs), e.g., American Sign Language (ASL), gerunds help express the meaning of ongoing actions and activities conveyed by verbs (Klima & Bellugi, 1979, p. 295). In spoken languages, a gerund is a form of the verb that functions as a noun and expresses the state of being or an ongoing action (Maekelberghe, 2020). Gerunds are complex constructions as they have nominal-verbal nature (Travis, 2005, p. 321) and morphological similarity with present participle or progressive aspect (Siegel, 1998). This research is motivated by the challenging nature of distinguishing gerund constructions at the morphological level, and research in sign …

From Prohibition To Preparation: Reframing Academic Integrity In The Age Of Ai, James Hutson

Faculty Scholarship

This study analyzes how U.S. universities reconfigure academic integrity during the 2024–2025 cycle in response to widespread generative AI adoption. The analysis foregrounds three loci: student ignorance and metacognitive blind spots; the expanded remit of Academic Integrity Officers prioritizing education over punishment; and deliberate AI-enabled misconduct that exposes the evidentiary limits of detection technologies. A mixed-methods design integrates a multi-site review at Arizona State University, Montclair State University, and Cornell University with synthesis of surveys, policies, and faculty development guidance. Findings show that detector outputs function as conversational prompts rather than adjudicative proof, necessitating dialogic resolution standards, process evidence, and …

The Ai-Powered Learning Loop In Higher Education, Oualid Abidi, Vladimir Dzenopoljac, Aleksandra Dzenopoljac

All Works

Purpose – This study examines how generative AI tools affect business students’ academic performance by investigating whether flexible AI policies promote deeper learning, enhance self-efficacy and facilitate tacit knowledge acquisition in a Middle Eastern context, while ensuring efficiency and academic integrity. Design/methodology/approach – A qualitative, exploratory study observed 20 final-year business students in Kuwait during five in-class activities using generative AI tools. Semi-structured interviews complemented the researcher’s observations. Thematic analysis revealed patterns in benefits, challenges and learning processes, leading to the development of the AI-powered learning loop framework to explain academic performance outcomes. Findings – The study indicates that generative …

Graph Perturbations For Robust Knowledge Discovery And Retrieval, Hanhua Xiao

Dissertations and Theses Collection (Open Access)

Graph perturbation, rooted in classical perturbation theory, studies how small topology edits, i.e., adding or deleting edges, affects graph properties (e.g., density, centrality). This fundamental problem underpins applications like bioinformatics, privacy preservation and system defense. While much prior work targets perturbations that influence global graph statistics or model outputs, comparatively little addresses robustness for knowledge discovery and information retrieval. In these settings, graphs are attributed: nodes carry real-world semantics (e.g., locations, people) and edges encode interactions or relationships. This thesis proposes new formulations and algorithms that generate and leverage graph perturbations to make knowledge discovery and retrieval more robust. Specifically, …

Enhancing Multi-View, Multi-Modal Sensing, Perception And Actuation For Edge Intelligence, Dhanuja Tharith Wanniarachchige

Dissertations and Theses Collection (Open Access)

Artificial Intelligence of Things (AIoT) technologies have ushered in exciting new advances in intelligent sensing, perception, and actuation for many real-world cyberphysical systems (CPS) applications. These technologies have had a formidable impact in domains such as large-scale video surveillance, autonomous transportation and robotics, precision healthcare, and industrial automation. In these applications, sensors and actuators are often collocated with processing nodes, and such nodes are typically interconnected via wireless networks. Vision-based machine intelligence, exemplified by tasks such as object detection, object tracking, and activity analysis, is a very common enabler of such CPS applications. Efficient execution of Deep Neural Network (DNN) …

Scaling Up Cooperative Multi-Agent Reinforcement Learning, Minghong Geng

Dissertations and Theses Collection (Open Access)

Multi-agent systems (MAS) involve multiple autonomous agents that coordinate their actions to achieve shared or competing objectives in dynamic environments. Over the past decade, multi-agent reinforcement learning (MARL) has emerged as a powerful paradigm for enabling collaborative behaviors among autonomous agents within MAS to solve complex tasks. This dissertation discusses a critical scalability gap that exists between current MARL capabilities and real-world deployment requirements. Most existing MARL research focuses on small-scale laboratory problems, often struggling to coordinate large agent populations and facing challenges with extended decision-making horizons. In contrast, many real-world applications demand coordination among hundreds or thousands of agents …

When It Comes To Scientific Information Extraction And Llms, Less Is More, Sameer Shaik

Theses and Dissertations from DePaul University

The scientific literature continues to expand rapidly, making manual extraction of structured scientific facts increasingly impractical. Traditional Machine Learning and Natural Language Processing (NLP) pipelines require large expert-annotated datasets, which are costly to produce. Novel Large Language Models (LLMs) face challenges in long-context scientific reasoning, hallucinations, and entity linking. This thesis investigates ELSIE-Blob, a domain-aware preprocessing method that segments scientific articles into compact text “blobs” containing components of entity relations (here, polymer names, melting point indicators, and numerical values). We test whether blob-based input allows lightweight, consumer-hardware-accessible LLMs to extract polymer–melting point (polymer–Tm) pairs accurately without training data. Experiments using …

The Impact Of Sanctions On Github Developers And Activities, Youmei Fan, Ani Hovhannisyan, Hideaki Hata, Christoph Treude, Raula G. Kula

Research Collection School Of Computing and Information Systems

The GitHub platform has fueled the creation of truly global software, enabling contributions from developers across various geographical regions of the world. As software becomes more entwined with global politics and social regulations, it becomes similarly subject to government sanctions. In 2019, GitHub restricted access to certain services for users in specific locations but rolled back these restrictions for some communities (e.g., the Iranian community) in 2021. We conducted a largescale empirical study, collecting approximately 156 thousand user profiles and their 41 million activity points from 2008 to 2022, to understand the response of developers. Our results indicate that many …

Sustainable Llm Inference For Edge Ai: Evaluating Quantized Llms For Energy Efficiency, Output Accuracy, And Inference Latency, Erik Johanne Husom, Arda Goknil, Merve Astekin, Lwin Khin Shar, Andre Kasen, Sagar Sen, Benedikt Andreas Mithassel, Ahmet Soylu

Research Collection School Of Computing and Information Systems

Deploying Large Language Models (LLMs) on edge devices presents significant challenges due to computational constraints, memory limitations, inference speed, and energy consumption. Model quantization has emerged as a key technique to enable efficient LLM inference by reducing model size and computational overhead. In this study, we conduct a comprehensive analysis of 28 quantized LLMs from the Ollama library, which applies by default Post-Training Quantization (PTQ) and weight-only quantization techniques, deployed on an edge device (Raspberry Pi 4 with 4GB RAM). We evaluate energy efficiency, inference performance, and output accuracy across multiple quantization levels and task types. Models are benchmarked on …

Enhancing Spatial Understanding In Mixed-Reality Presentations, Nam-Dang Vo, Van-Vinh Thai, Nam-Hoi Do, Viet-Tham Huynh, Anthony Tang, Khan-Duy Le

Research Collection School Of Computing and Information Systems

Mixed reality (MR) presentations often involve a presenter wearing a head-mounted display (HMD) and an audience watching via a large display, making it difficult for audiences to perceive spatial relationships between the presenter and virtual objects. We report two experiments testing three design variations: (1) scene camera placement (audience-aligned vs. opposite), (2) overlaying the presenter’s first-person view, and (3) highlighting objects in the presenter’s view. Results show that audience-aligned cameras and object highlighting improve spatial understanding, while combining third- and first-person views can further aid perception. We derive design guidelines for configuring MR presentations to better support audience comprehension.

Disc: Decentralized Identity System With Self-Sovereign Credential Aggregation, Yang Yang, Wai Keung Ching, Minming Huang, Supachate Innet, Guomin Yang, Hwee Hwa Pang, Robert H. Deng

Research Collection School Of Computing and Information Systems

The evolution of decentralized identity (DID) and self-sovereign identity (SSI) frameworks, as endorsed by W3C Verifiable Credentials (VC) and eIDAS 2.0, underscores the need for secure, efficient, and privacy-preserving credential management. However, existing credential systems often depend on centralized issuers, lack efficient aggregation mechanisms, or fail to ensure unlinkability across authentication sessions. To address these challenges, we propose DISC (Decentralized Identity System with Self-Sovereign Credential Aggregation), a novel credential system that enables multi-authority credential issuance, user-controlled credential aggregation, and unlinkable authentication. DISC allows users to aggregate credentials from multiple issuers while maintaining constant-size authentication tokens and supporting batch verification for …

Addressing Sparsity For Knowledge Graph Completion: Data And Model Perspectives, Ran Liu

Dissertations and Theses Collection (Open Access)

Knowledge graphs (KGs) are powerful tools for structuring factual knowledge into relational triples, yet their practical utility is often adversely affected by data sparsity. Many entities and relations are associated with only a few observations, which limits the quality of learned embeddings and weakens generalization in downstream tasks. The problem of sparsity led to two interrelated challenges. Firstly, it restricts the informativeness of training samples: positive examples are scarce, and conventional negative sampling often produces trivial or redundant negatives that resulting in limited guidance. Secondly, in few-shot relation learning scenarios, sparsity worsens distribution shifts between training and test relations, as …

Attorneys And Ai: How Lawyers Use Artificial Intelligence And Analyze Its Impacts, Matthew I. Hall, Christian Turner, Eddie A. Gomez Schieber, Nathaniel Kite, Ari Schlesinger

Scholarly Works

AI systems are testing lawyers' professional ethics obligations of competence, confidentiality, and candor. In the legal profession, the widespread availability of AI systems presents opportunities, like improving the review of documents during the discovery stage of a lawsuit, and challenges, illustrated by the handful of high-profile incidents where lawyers submitted legal briefs in court citing and describing fictitious cases based on AI-generated output. We conducted interviews with 44 legal professionals in the U.S. to understand how attorneys are making sense of AI technology and the impacts these technologies are having on their profession, legal ethics, and legal institutions. We describe …

Enhancing It Security Management With An Advanced Intrusion Detection System Based On Machine Learning And Explainable Ai, Hanan Aslam Al Zubaidi

Theses

The fast changing landscape of cyber threats continues to challenge the development of strong and reliable security frameworks for IT management systems. Traditional defense tools, such as Intrusion Detection Systems (IDS), often struggle to keep up with today's advanced and constantly evolving attack methods. This thesis explores these ongoing challenges and looks into how machine learning (ML) and explainable artificial intelligence (XAI) can be used to boost IDS performance.

The research outlines a smart, adaptive system that combines supervised learning for real-time threat detection, unsupervised models for anomaly analysis, and proactive defense strategies. The goal is to improve detection accuracy, …

Context-Aware Hierarchical Taxonomy Generation For Scientific Papers Via Llm-Guided Multi-Aspect Clustering, Kun Zhu, Lizi Liao, Yuxuan Gu, Lei Huang, Xiaocheng Feng, Bing Qin

Research Collection School Of Computing and Information Systems

The rapid growth of scientific literature demands efficient methods to organize and synthesize research findings. Existing taxonomy construction methods, leveraging unsupervised clustering or direct prompting of large language models (LLMs), often lack coherence and granularity. We propose a novel context-aware hierarchical taxonomy generation framework that integrates LLM-guided multi-aspect encoding with dynamic clustering. Our method leverages LLMs to identify key aspects of each paper (e.g., methodology, dataset, evaluation) and generates aspect-specific paper summaries, which are then encoded and clustered along each aspect to form a coherent hierarchy. In addition, we introduce a new evaluation benchmark of 156 expert-crafted taxonomies encompassing 11.6k …

Why Stop At One Error? Benchmarking Llms As Data Science Code Debuggers For Multi-Hop And Multi-Bug Errors, Zhiyu Yang, Shuo Wang, Yukun Yan, Yang Deng

Research Collection School Of Computing and Information Systems

LLMs are transforming software development, yet current code generation and code repair benchmarks mainly assess syntactic and functional correctness in simple, single-error cases. LLMs’ capabilities to autonomously find and fix runtime logical errors in complex data science code remain largely unexplored. To address this gap, we introduce DSDBench: the Data Science Debugging Benchmark, the first benchmark for systematic evaluation of LLMs on multi-hop error tracing and multi-bug detection in data science code debugging. DSDBench adapts datasets from existing data science task benchmarks, such as DABench and MatPlotBench, featuring realistic data science debugging tasks with automatically synthesized multi-hop, multi-bug code snippets. …

Image Captioning Through The Lens Of The Gricean Maxims: Generating Meaningful And Relevant Image Descriptions, Annika Lindh

Doctoral

Image captioning models enable us to automatically generate natural language image descriptions for previously unseen images. It combines the two fields of computer vision and natural language generation, allowing models to interpret the con tent of an image and communicate that knowledge through natural language text.

Research into image captioning has the potential benefit of reducing the gap in digital information availability between fully sighted individuals and those who are visually impaired. However, automatically generated captions often fail to provide the required level of detail and specificity to achieve this goal. Furthermore, current standard evaluation methods are insufficient at measuring …

Defects4c: Benchmarking Large Language Model Repair Capability With C/C++ Bugs, Jian Wang, Xiaofei Xie, Qiang Hu, Shangqing Liu, Jiongchi Yu, Jiaolong Kong, Yi Li

Research Collection School Of Computing and Information Systems

Automated Program Repair (APR) plays a critical role in enhancing the quality and reliability of software systems. While substantial progress has been made in Java-based APR, largely facilitated by benchmarks like Defects4J, there remains a significant gap in research on C/C++ program repair, despite the widespread use of C/C++ and the prevalence of associated vulnerabilities. This gap is primarily due to the lack of high-quality, open-source benchmarks tailored for C/C++. To address this issue, we introduce Defects4C, a comprehensive and executable benchmark specifically designed for C/C++ program repair. Our dataset is constructed from real-world C/C++ repositories and includes a large …

Distillcaps: Enhancing Audio-Language Alignment In Captioning Via Retrieval-Augmented Knowledge Distillation, Thinh Pham, Nghiem Diep, Lizi Liao, Binh Nguyen

Research Collection School Of Computing and Information Systems

Automated audio captioning (AAC) benefits from incorporatingexternal context to interpret complex sounds, but doing so withretrieval-augmented generation (RAG) at inference is sometimesinfeasible due to data availability or incurs significant latency andcomplexity. We propose DistillCaps, a novel training-time frame-work that leverages RAG to guide knowledge distillation for im-proved audio-language alignment, while lessening the relianceon retrieval during inference. In our framework, a RAG-equippedteacher model retrieves relevant textual information (e.g., simi-lar captions) for each audio clip and uses it for training to gener-ate context-enriched captions. Simultaneously, a student model istrained to imitate this teacher, learning to produce high-qualitycaptions from audio alone. We further …

Instructors’ Strategies In Creating And Implementing Constructivist Llm-Based Learning Activities, Emily Aurelia, Shun Yi Yeo, Michelle Lui, Effie Lai-Chong Law, Anthony Tang

Research Collection School Of Computing and Information Systems

Large language models (LLMs) are increasingly being integrated into educational settings, enabling more adoption of constructivist teaching and learning approaches in classrooms. This paper explores the strategies instructors are currently using to incorporate LLMs into learning activities that align with constructivist principles, which emphasize that learners actively construct their own knowledge. Through interviews with nine instructors who have designed eleven distinct LLM-based activities and using reflexive thematic analysis, this study identifies various types of learning activities with respect to four different aspects of the constructivist learning theory. The strategies employed and challenges faced to foster constructivist student-LLM interaction were also …

Enhancing The Acceptability Of Decision-Making System Using Xai Case: Crime Profiling System, Mohamed Saeed Al Shamsi

Theses

In the current world, we need to place more emphasis on how easily interpretable, accurate, and acceptable data analysis results are, given that essential operations in law enforcement, among other sectors, are backed up by the use of complex computing systems. Crime profiling systems that use crime data for profiling encounter major problems because they depend on algorithm-based methods. These methods can be ambiguous and inaccurate, leading to low public acceptability. The study investigates major problems with Complex Crime profiling systems (CPS) because their unexplained algorithms result in system performance issues and public scepticism. XAI provides a solution to handle …

Enhanced Privacy Preserving Healthcare Data Management With Federated Learning Using Homomorphic Encryption, Omar Abdulla Ali

Theses

Federated Learning (FL) is a decentralized approach of machine learning on multiple clients jointly training models without sharing their raw data, which drastically improves privacy and enhance protection against security breach. This is particularly critical in the healthcare sector, where hospitals and medical institutions are often unable to exchange patient records due to strict privacy regulations and data-management policies. However, there is still a risk of privacy breach when clients send their model updates to the central server, because if a model update is intercepted or analyzed by a malicious entity, it could be used to recover sensitive data using …

Advancing Security Safeguards In Large Language Models Through Multi-Agent Systems, Mohammed Rashed Alnuaimi

Theses

This thesis focused on enhancing the safe use of Large Language Model (LLM) through the innovative use of a Multi-Agent System (MAS). As LLMs like ChatGPT became essential to our everyday interactions, the need to maintain the safe use of these systems increased. This research thoroughly assessed the current security measures in place for LLM, pointed out their limitations and developed new and more effective security strategies. The core of the proposed solution was a MAS designed to ensure that all data processed by LLM met guidelines including Privacy, Confidentiality, and Ethical standards before reaching the user. The system involved …

Evaluating Large Language Models For Automated Cv Ranking: A Hybrid Embedding Approach For Enhanced Recruitment, Sarah Mohamed Alhindaassi

Theses

Increasing numbers of applications have revealed limitations in legacy keyword-filtering-based Applicant Tracking Systems (ATS), which commonly overlook candidate potential and ignore contextual or transferable skills. Advances in Natural Language Processing (NLP) and Large Language Models (LLMs) offer an exhilarating alternative, supporting context-sensitive and human-crafted reasoning in candidate evaluation. This thesis systematically evaluates four classes of approaches, lexical models, embedding-based methods, Large Language Models (LLMs), and hybrid ensembles, for automation of Curriculum Vitae (CV) to Job Description (JD) matching without exploiting prior annotations or annotations at match time. Using a combination of publicly available datasets and real-world sample data covering three …

Detecting Data Poisoning Attacks In Medical Imaging: A Study On Chest X-Ray Classification Tasks, Akhila Abdulla Asgar

Theses

This thesis examines the vulnerability of AI medical imaging models to adversarial threats, with a specific focus on data poisoning attacks in chest X-ray classification. The study begins with a Systematic Literature Review (SLR) to assess the existing adversarial attacks and defenses in medical imaging, revealing a significant research gap in studies exploring data poisoning attacks in the medical domain. Based on our literature search, an efficient and lightweight defense, namely friendly noise defense, against data poisoning has not been investigated in medical imaging classification tasks. Hence, in this work, we investigated its effectiveness on the chest X-ray dataset, and …

Security Modelling For Cyber-Physical Systems: A Systematic Literature Review, Shao Fei Huang, Christopher M. Poskitt, Lwin Khin Shar

Research Collection School Of Computing and Information Systems

Cyber-physical systems are at the intersection of digital technology and engineering domains, rendering them high-value targets of sophisticated and well-funded cybersecurity threat actors. Prominent cybersecurity attacks on CPS have brought attention to the vulnerability of these systems and the inherent weaknesses of critical infrastructure reliant on them. Security modelling for CPS is an important mechanism to systematically identify and assess vulnerabilities, threats, and risks throughout system life cycles, and to ultimately ensure system resilience, safety, and reliability. This survey delves into state-of-the-art research on CPS security modelling, encompassing both threat and attack modelling. While these terms are sometimes used interchangeably, …

Simulated Interactive Debugging, Yannic Noller, Erick Chandra, Srinidhi Chandrashekar, Kenny Choo, Cyrille Jegourel, Oka Kurniawan, Christopher M. Poskitt

Research Collection School Of Computing and Information Systems

Debugging software, i.e., the localization of faults and their repair, is a key activity in software engineering. Therefore, effective and efficient debugging is one of the core skills a software engineer must develop. However, the teaching of debugging techniques is usually very limited or only taught in indirect ways, e.g., during software projects. As a result, most Computer Science (CS) students learn debugging only in an ad-hoc and unstructured way. In this work, we present our approach called Simulated Interactive Debugging that interactively guides students along the debugging process. The guidance aims to empower the students to repair their solutions …

Towards Goal-Oriented Intelligent Tutoring Systems In Online Education, Yang Deng, Zifeng Ren, An Zhang, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Interactive Intelligent Tutoring Systems (ITSs) enhance the learning experience in online education byfostering effective learning through interactive problem-solving. However, many current ITS models do notfully incorporate proactive engagement strategies that optimize educational resources through thoughtfulplanning and assessment. In this work, we propose a novel and practical task of Goal-oriented IntelligentTutoring Systems (GITS), designed to help students achieve proficiency in specific concepts through a tailoredsequence of exercises and evaluations. We introduce a novel graph-based reinforcement learning framework,named Planning-Assessment-Interaction (PAI), to tackle the challenges of goal-oriented policy learningwithin GITS. This framework utilizes cognitive structure information to refine state representation andguide the selection …