Computer Sciences Commons^™

Knowledge Boundary Of Large Language Models: A Survey, Moxin Li, Yong Zhao, Wenxuan Zhang, Shuaiyi Li, Wenya Xie, See-Kiong Ng, Tat-Seng Chua, Yang Deng

Research Collection School Of Computing and Information Systems

Although large language models (LLMs) store vast amount of knowledge in their parameters, they still have limitations in the memorization and utilization of certain knowledge, leading to undesired behaviors such as generating untruthful and inaccurate responses. This highlights the critical need to understand the knowledge boundary of LLMs, a concept that remains inadequately defined in existing research. In this survey, we propose a comprehensive definition of the LLM knowledge boundary and introduce a formalized taxonomy categorizing knowledge into four distinct types. Using this foundation, we systematically review the field through three key lenses: the motivation for studying LLM knowledge boundaries, …

Beware Of Your Po! Measuring And Mitigating Ai Safety Risks In Role-Play Fine-Tuning Of Llms, Weixiang Zhao, Yulin Hu, Yang Deng, Jiahe Guo, Xingyu Sui, Xinyang Han, An Zhang, Yanyan Zhao, Bing Qin, Tat-Seng Chua, Ting Liu

Research Collection School Of Computing and Information Systems

Although large language models (LLMs) store vast amount of knowledge in their parameters, they still have limitations in the memorization and utilization of certain knowledge, leading to undesired behaviors such as generating untruthful and inaccurate responses. This highlights the critical need to understand the knowledge boundary of LLMs, a concept that remains inadequately defined in existing research. In this survey, we propose a comprehensive definition of the LLM knowledge boundary and introduce a formalized taxonomy categorizing knowledge into four distinct types. Using this foundation, we systematically review the field through three key lenses: the motivation for studying LLM knowledge boundaries, …

Browsing Like Human: A Multimodal Web Agent With Experiential Fast-And-Slow Thinking, Haohao Luo, Jiayi Kuang, Wei Liu, Ying Shen, Jian Luan, Yang Deng

Research Collection School Of Computing and Information Systems

Automating web navigation which aims to build a web agent that follows user instructions to complete tasks like booking flights by interacting with websites, has received increasing attention due to its practical value. Although existing web agents are mostly equipped with visual perception, planning, and memory abilities, their reasoning process are still deviate from human cognition. In this work, we study the human thought pattern to empower agent with more human-like abilities in web navigation. To tackle this problem, we propose a novel multimodal web agent framework called WebExperT, which is designed to emulate the human planning process of “thinking …

Coleclip: Open-Domain Continual Learning Via Joint Task Prompt And Vocabulary Learning, Yukun Li, Guansong Pang, Wei Suo, Chenchen Chen, Yuling Xi, Lingqiao Liu, Hao Chen, Guoqiang Liang, Peng Wang

Research Collection School Of Computing and Information Systems

This article investigates the problem of continual learning (CL) of vision-language models (VLMs) in open domains, where models are required to perform continual updating and inference on a stream of datasets from diverse seen and unseen domains with novel classes. Such a capability is crucial for various applications in open environments, e.g., AI assistants, autonomous driving systems, and robotics. Current CL studies mostly focus on closed-set scenarios in a single domain with known classes. Large pretrained VLMs such as CLIP have showcased exceptional zero-shot recognition capabilities, and several recent studies have leveraged the unique characteristics of VLMs to mitigate catastrophic …

Other Orienteering Problem Variants, Pieter Vansteenwegen, Aldy Gunawan

Research Collection School Of Computing and Information Systems

In this chapter, different variants of routing problems with profits will be discussed. Based on what is available in literature, mostly variants of the orienteering problem will be discussed. A first variant considers capacity constraints, since these appear frequently in many practical applications. Next, multi-objective orienteering problems, explicitly considering different types of profits separately are discussed. Time-dependent and stochastic travel times are also relevant for most practical applications. These are considered together with time-dependent and stochastic profits. More and more routing problems are considered together with inventory management. For routing problems with profits, this leads to the inventory orienteering problem, …

A Review: The Beauty Of Serendipity Between Integrated Circuit Security And Artificial Intelligence, Chen Dong, Decheng Qiu, Bolun Li, Yang Yang, Chenxi Lyu, Dong Cheng, Hao Zhang, Zhenyi. Chen

Research Collection School Of Computing and Information Systems

Integrated circuits are the core of a cyber-physical system, where tens of billions of components are integrated into a tiny silicon chip to conduct complex functions. To maximize utilities, the design and manufacturing life cycle of integrated circuits rely on numerous untrustworthy third parties, forming a global supply chain model. At the same time, this model produces unpredictable and catastrophic issues, threatening the security of individuals and countries. As for guaranteeing the security of ultra-highly integrated chips, detecting slight abnormalities caused by malicious behavior in the current and voltage is challenging, as is achieving computability within a reasonable time and …

Eformer: An Effective Edge-Based Transformer For Vehicle Routing Problems, Dian Meng, Zhiguang Cao, Yaoxin Wu, Yaqing Hou, Hongwei Ge, Qiang Zhang

Research Collection School Of Computing and Information Systems

Recent neural heuristics for the Vehicle Routing Problem (VRP) primarily rely on node coordinates as input, which may be less effective in practical scenarios where real cost metrics--such as edge-based distances--are more relevant. To address this limitation, we introduce EFormer, an Edge-based Transformer model that uses edge as the sole input for VRPs. Our approach employs a precoder module with a mixed-score attention mechanism to convert edge information into temporary node embeddings. We also present a parallel encoding strategy characterized by a graph encoder and a node encoder, each responsible for processing graph and node embeddings in distinct feature spaces, …

Ai-Assisted Triage And Decision Support Of Head And Neck Cancer Screening And Diagnosis In Low-Resourced Settings, Min Hun Lee, Sean Shao Wei Lam, Shaun Xin Hong Liew, Michael Dorosan, Nicholas Graves, Jonas Karlström, Hiang Khoon Tan, Walter Tsong Lee

Research Collection School Of Computing and Information Systems

The mortality burden of head and neck cancer (HNC) is increasing globally and disproportionately affects people in low-and middle-income countries with limited medical workforce. To address this issue, artificial intelligence (AI) algorithms are increasingly being explored to process medical imaging data, demonstrating competitive performance. However, the clinical adoption of AI remains challenging as clinicians struggle to understand how complex AI works and trust it to use in practice. In addition, AI may not perform well on varying data qualities of endoscopy videos for HNC screening and diagnosis from multiple sites.In this project, our international and interdisciplinary team will collaborate with …

Debate, Reflect, And Distill: Multi-Agent Feedback With Tree-Structured Preference Optimization For Efficient Language Model Enhancement, Xiaofeng Zhou, Heyan Huang, Lizi Liao

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) continue to set new standards in knowledge-intensive and complex reasoning tasks, yet their high computational demands limit widespread adoption. While distilling large models into smaller ones offers a sustainable solution, current techniques—such as static knowledge distillation, resource-intensive reinforcement learning from human feedback, or limited self-reflection—struggle to yield substantial and lasting performance gains. In this paper, we present a novel Debate and Reflect (D&R) framework that orchestrates multi-turn debates between smaller models and stronger teacher models, eliciting actionable feedback (e.g., error analysis, corrective strategies) to guide student models. Further, we introduce Tree-structured Direct Preference Optimization (T-DPO) to …

Memotune: A Measure And Moment-Driven Fine-Tuning Framework For Quantized Large Language Models, Yun Zhang, Xue Geng, Lizi Liao, Jintong Sun, Minghe Yu, Ge Yu

Research Collection School Of Computing and Information Systems

Quantizing large language models (LLMs) is essential for reducing memory and computational costs in natural language processing. Existing methods combine quantization with parameter-efficient fine-tuning but often fail to meet practical performance requirements. This paper introduces MeMoTune, a novel fine-tuning framework for quantized LLMs. By employing a measure and moment approach within a low-rank approximation framework in probability measure space, MeMoTune optimizes the objective function for superior fine-tuning results. The update process is further refined through scaled gradient, enhancing convergence efficiency and noise robustness. Experiments on tasks like text generation, summarization, and understanding show MeMoTune significantly outperforms state-of-the-art methods, e.g. fine-tuning …

Xfinbench: Benchmarking Llms In Complex Financial Problem Solving And Reasoning, Zhihan Zhang, Yixin Cao, Lizi Liao

Research Collection School Of Computing and Information Systems

Solving financial problems demands complex reasoning, multimodal data processing, and a broad technical understanding, presenting unique challenges for current large language models (LLMs). We introduce **XFinBench**, a novel benchmark with 4,235 examples designed to evaluate LLM’s ability in solving comple**X**, knowledge-intensive **Fin**ancial problems across diverse graduate-level finance topics with multi-modal context. We identify five core capabilities of LLMs using XFinBench, i.e., _terminology understanding_, _temporal reasoning_, _future forecasting_, _scenario planning_, and _numerical modelling_. Upon XFinBench, we conduct extensive experiments on 18 leading models. The result shows that o1 is the best-performing text-only model with an overall accuracy of 67.3%, but still …

Connecting Giants: Synergistic Knowledge Transfer Of Large Multimodal Models For Few-Shot Learning, Hao Tang, Shengfeng He, Jing Qin

Research Collection School Of Computing and Information Systems

Few-shot learning (FSL) addresses the challenge of classifying novel classes with limited training samples. While some methods leverage semantic knowledge from smaller-scale models to mitigate data scarcity, these approaches often introduce noise and bias due to the data's inherent simplicity. In this paper, we propose a novel framework, Synergistic Knowledge Transfer (SYNTRANS), which effectively transfers diverse and complementary knowledge from large multimodal models to empower the off-the-shelf few-shot learner. Specifically, SYNTRANS employs CLIP as a robust teacher and uses a few-shot vision encoder as a weak student, distilling semantic-aligned visual knowledge via an unsupervised proxy task. Subsequently, a training-free synergistic …

Ai-Assisted Risk Assessment In Generative Ai Governance, Wu Jiaqi Young, Fiona Fui-Hoon Nah

Research Collection School Of Computing and Information Systems

Effective risk assessment is paramount for responsible generative AI (GenAI) deployment. Traditional governance approaches that rely on manual reviews are inadequate given the scale and velocity of GenAI outputs. A risk-based approach incorporating real-time monitoring and governance is paramount. In this research, we examine how the efficacy of suggestive versus supportive explanations for AI’s risk assessment of GenAI outputs is moderated by user domain expertise and AI’s risk assessment in determining user acceptance. We hypothesize that cognitive involvement increases with AI’s risk assessment, with higher risks triggering more critical evaluation. By drawing on the elaboration likelihood model, we hypothesize that …

Freqllm: Frequency-Aware Large Language Models For Time Series Forecasting, Shunan Wang, Min Gao, Zongwei Wang, Yibing Bai, Feng Jiang, Guansong Pang

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) have recently shown promise in Time Series Forecasting (TSF) by effectively capturing intricate time-domain dependencies. However, our preliminary experiments reveal that standard LLM-based approaches often fail to capture global correlations, limiting predictive performance. We found that embedding frequency-domain signals smooths weight distributions and enhances structured correlations by clearly separating global trends (low-frequency components) from local variations (high-frequency components). Building on these insights, we propose FreqLLM, a novel framework that integrates frequency-domain semantic alignment into LLMs to refine prompts for improved time series analysis. By bridging the gap between frequency signals and textual embeddings, FreqLLM effectively captures …

Fine‑Tuning Multimodal Large Language Models For Product Bundling, Xiaohao Liu, Jie Wu, Zhulin Tao, Yunshan Ma, Yinwei Wei, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Recent advances in product bundling have leveraged multimodal information through sophisticated encoders, but remain constrained by limited semantic understanding and a narrow scope of knowledge. Therefore, some attempts employ In-context Learning (ICL) to explore the potential of large language models (LLMs) for their extensive knowledge and complex reasoning abilities. However, these efforts are inadequate in understanding mulitmodal data and exploiting LLMs' knowledge for product bundling. To bridge the gap, we introduce Bundle-MLLM, a novel framework that fine-tunes LLMs through a hybrid item tokenization approach within a well-designed optimization strategy. Specifically, we integrate textual, media, and relational data into a unified …

Llm2rec: Large Language Models Are Powerful Embedding Models For Sequential Recommendation, Yingzhi He, Xiaohao Liu, An Zhang, Yunshan Ma, Tat‑Seng Chua

Research Collection School Of Computing and Information Systems

Sequential recommendation aims to predict users' future interactions by modeling collaborative filtering (CF) signals from historical behaviors of similar users or items. Traditional sequential recommenders predominantly rely on ID-based embeddings, which capture CF signals through high-order co-occurrence patterns. However, these embeddings depend solely on past interactions, lacking transferable knowledge to generalize to unseen domains. Recent advances in large language models (LLMs) have motivated text-based recommendation approaches that derive item representations from textual descriptions. While these methods enhance generalization, they fail to encode CF signals-i.e., latent item correlations and preference patterns-crucial for effective recommendation. We argue that an ideal embedding model …

Reimagining Education With Ai, Margherita Pagani, Steven M. Miller, Jerry Wind

Research Collection School Of Computing and Information Systems

This chapter examines AI’s transformative potential in education, focusing on Generative AI (GenAI) and Large Language Models (LLMs) while at the same time emphasizing the importance of grounding and guiding AI efforts with learning science and education research findings. It synthesizes analyses and expert recommendations, highlighting opportunities like personalized learning and enhanced teacher productivity, alongside challenges such as over-reliance on AI. Practical steps for instructors include adopting a question-first approach, utilizing AI for personalized feedback, designing AI-enhanced learning experiences, fostering critical thinking, and ensuring ethical AI use. The chapter concludes with strategic recommendations for leveraging AI to sustainably improve educational …

Dreamanime: Learning Style-Identity Textual Disentanglement For Anime And Beyond, Chenshu Xu, Yangyang Xu, Huaidong Zhang, Xuemiao Xu, Shengfeng He

Research Collection School Of Computing and Information Systems

Text-to-image generation models have significantly broadened the horizons of creative expression through the power of natural language. However, navigating these models to generate unique concepts, alter their appearance, or reimagine them in unfamiliar roles presents an intricate challenge. For instance, how can we exploit language-guided models to transpose an anime character into a different art style, or envision a beloved character in a radically different setting or role? This paper unveils a novel approach named DreamAnime, designed to provide this level of creative freedom. Using a minimal set of 2-3 images of a user-specified concept such as an anime character …

Intersecting Realities And Evolving Landscapes: Mapping Generative Ai Within The Framework Of Digital Rhetoric, Joshua Troy Nieubuurt

English Theses & Dissertations

The increased usage of [Generative] AI technologies (GenAI) in the 21st century has called into the question the rhetorical agency of these digital things. [Gen]AI has historically been framed within a Heideggerian “readiness-to-hand” dynamic in which it has been unilaterally conceived as a tool to be used by humans. This dissertation proposes that the GenAI assemblage is capable of being a co-actor in rhetorical spaces. To provide evidence for this stance This dissertation utilizes Actor Network Theory to map the actants within a GenAI assemblage. In doing so it allows for an understanding of the stakeholders (both human and non-human) …

Service With A Smile Or Salesperson Mirroring? Understanding The Flow Of Emotional Contagion In Sales Encounters, Vinh Quoc Trong Luong

Theses and Dissertations in Business Administration

This study examines the directionality of emotional contagion in sales interactions, addressing a critical gap in understanding whether emotions flow primarily from the salesperson to the customer, from the customer to the salesperson, or bidirectionally. While prior research emphasizes customer-driven emotional flow or bidirectional alignment, this study challenges these assumptions by employing categorical Cross-Recurrence Quantification Analysis (CRQA) to assess temporal emotional synchronization in sales dialogues. Leveraging automated sentiment analysis and multi-agent AI evaluation for performance metrics, the research analyzes 166 sales interactions to quantify emotional influence dynamics. Results reveal that salespeople predominantly lead emotional exchanges, exhibiting stronger and more stable …

Unfolding Particle Detector Effects And Solving Qcd Inverse Problem With Generative Ai, Tareq Saeed Alghamdi

Computer Science Theses & Dissertations

Advancements in artificial intelligence (AI) have revolutionized high-energy physics by enabling generative models to address key detector-related Challenges. This work explores the generative model to mitigate smearing, acceptance, and inefficiency in particle detectors, enhancing experimental precision.

We present a generative model-based framework to model and correct detector distortions. Using the Jefferson Lab CLAS g11 experiment as a case study, our approach successfully unfolds detector effects in multi-particle final states while preserving multidimensional correlations despite complex reaction mechanisms. A key focus is addressing the acceptance problem—accurately modeling detector acceptance without computationally expensive simulations. By training generative model-based framework on simulated detector …

Network Intelligence For Next-Generation Wireless Networks: Advancing Distribution And Coordination, Yonatan Melese Worku

Electrical and Computer Engineering ETDs

Next-generation wireless networks, encompassing 6G and beyond, face rigorous demands for ultra-low latency, ubiquitous connectivity, exceptionally high data rates, and robust security, necessitating innovative approaches to resource optimization and network protection. This dissertation proposes a pioneering framework that synergizes advanced methodologies—deep reinforcement learning, deep learning, blockchain, and multi-agent systems—to address these challenges. Distributed architectures, underpinned by AI-driven multi-agent systems, form the backbone of this framework, enabling seamless integration and intelligent orchestration across diverse domains. The research advances IoT-based systems leveraging machine learning for resource efficiency in healthcare applications, develops reinforcement learning-driven frameworks to optimize energy and coverage for Unmanned Aerial …

Reviving The Lost Art: Historical Foundations And Future Pathways For Bespoke Service In Luxury Retail, Andrew Burnstine

Faculty and Staff Publications & Presentations

The mid-20th century witnessed a zenith of deeply personalized, bespoke service within iconic luxury specialty retailers. This paper critically analyzes the foundational principles of this historical bespoke service model, extending Service-Dominant (S-D) Logic and retail evolution theory, to propose a robust framework for its modern revival. Employing a rigorous qualitative, multiple-case study approach, grounded in extensive historical and media analysis of four archetypal American and British luxury boutiques, and uniquely informed by an insider-ethnographic perspective on the central case exemplar ("Martha's"), the study distills six core principles: Profound Client Knowledge, Visionary Curation & Styling, Anticipatory & Proactive Service, The Exclusive …

Combination Of Irreversible Electroporation And Clostridium Novyi-Nt Bacterial Therapy For Colorectal Liver Metastasis, Zigeng Zhang, Guangbo Yu, Qiaoming Hou, Farideh Amirrad, Sha Webster, Surya M. Nauli, Jianhua Yu, Vahid Yaghmai, Aydin Eresen, Zhuoli Zhang

Pharmacy Faculty Articles and Research

Colorectal liver metastasis (CRLM) poses a significant challenge in oncology due to its high incidence and poor prognosis in unresectable cases. Current treatments, including surgical resection, systemic chemotherapy, and liver-directed therapies, often fail to effectively target hypoxic tumor regions, which are inherently more resistant to these interventions. This review examines the potential of a novel therapeutic strategy combining irreversible electroporation (IRE) ablation and Clostridium novyi-nontoxic (C. novyi-NT) bacterial therapy. IRE is a non-thermal tumor ablation technique that uses high-voltage electric pulses to create permanent nanopores in cell membranes, leading to cell death while preserving surrounding structures, and …

More Everything Forever: Ai Overlords, Space Empires, And Silicon Valley’S Crusade To Control The Fate Of Humanity, Joseph Kirby

Consensus

Becker, A. (2025). More everything forever : AI overlords, space empires, and Silicon Valley’s crusade to control the fate of humanity. Basic Books. ISBN: 9781541619593

Teaching Ai Ethics And Skepticism: The Impact Of Instruction On Ethical Usage On Students’ Perceptions, Jenna D. Justin

Journal of Practitioner Research

This study investigates the ethical implications of artificial intelligence (AI) in K-12 education, focusing on how explicit instruction influences students' perceptions of AI tools like ChatGPT. Conducted with 80 sixth-grade students at A.D. Henderson University School and FAU High School, the research tracks changes in student understanding and skepticism of AI following a World History unit. Pre- and post-instruction surveys revealed a decline in comfort with AI as students became more aware of its ethical concerns, including plagiarism, bias, and misinformation. The findings suggest integrating AI ethics into the middle school curriculum to foster responsible AI usage among students.

Securing Ai-Generated Code, Andreas E. Nelson

Scholarly Horizons: University of Minnesota, Morris Undergraduate Journal

The increasing use of AI for code generation presents significant security challenges, as these tools often lack inherent security awareness and can produce vulnerable code. This paper investigates these security risks, outlining common types of vulnerabilities (such as injection flaws and improper resource handling) found in AI-generated code. It further explores and evaluates mitigation techniques aimed at im-proving code security, including model fine-tuning and adversarial strategies like Security Verifier Enhanced Neural Steering (SVEN). Findings indicate that while current methods offer promising ways to reduce vulnerabilities, ongoing research and development are crucial for the secure and responsible deployment of AI in …

Research On Policy Representation In Deep Reinforcement Learning, Zhen Chen, Zhuoyi Wu, Lin Zhang

Journal of System Simulation

Abstract: Deep reinforcement learning (DRL) has achieved remarkable success in various domains. Nevertheless, existing policy networks in DRL still face significant challenges in areas such as generalizability, multi-task adaptability, and sample efficiency. Policy representation, as a crucial research direction for enhancing DRL capabilities, aims to improve an agent's adaptability to environmental changes and novel tasks by constructing more efficient and generalizable forms of policy expression. This paper provided a concise overview of key research advances in the field of policy representation. It introduced diverse policy architectures, ranging from traditional multi-layer perceptron (MLP) -based policies to those based on pointer networks, …

Ai Project Facilitation Guidance For Research Computing And Data (Rcd) Professionals, Anna Alber, Laura Briggs, Paul Brunk, Manasvita Joshi, Atish P. Kamble, Amira Kefi, Timothy Middelkoop, Semir Sarajlic, Ana Maria Sokovic, Jeffrey N. Valdez, Ying Zhang

Administration and Staff Articles and Research

The role of Artificial Intelligence (AI) in research and education continues to rapidly grow, resulting in increased collaboration between researchers in AI and Research Computing and Data (RCD) professionals to meet the research and teaching demands. RCD professionals bridge the gap between research and technology by guiding and collaborating with researchers and educators through the process of selecting the hardware, software, and services best suited for executing their AI projects. This includes ensuring compliance with funding and regulatory requirements across the entire lifecycle of the project. In this paper, we present an overview of the AI project lifecycle and how …

A Web Application For Generating Argument Maps For Essays Using Llms, Alexis R. Chalmers

Theses

Argumentative writing is a critical skill that strengthens students’ reasoning, communication, and analytical abilities. However, maintaining a clear and organized argument structure while writing can be challenging. Argument maps — visual diagrams which explicitly show an argument’s structure — have been shown to improve students’ writing, but are rarely used outside of the planning stage of an essay due to the time and effort required to create them. Automatically generating argument maps from student essays helps students to evaluate the structure of their argument as they write and makes identifying unsupported claims visible. To evaluate whether large language models (LLMs) …