Computer Sciences Commons^™

Chain-Of-Exemplar: Enhancing Distractor Generation For Multimodal Educational Question Generation, Haohao Luo, Yang Deng, Ying Shen, See-Kiong Ng, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Multiple-choice questions (MCQs) are important in enhancing concept learning and student engagement for educational purposes. Despite the multimodal nature of educational content, current methods focus mainly on text-based inputs and often neglect the integration of visual information. In this work, we study the problem of multimodal educational question generation, which aims at generating subject-specific educational questions with plausible yet incorrect distractors based on multimodal educational content. To tackle this problem, we introduce a novel framework, named Chain-of-Exemplar (CoE), which utilizes multimodal large language models (MLLMs) with Chain-of-Thought reasoning to improve the generation of challenging distractors. Furthermore, CoE leverages three-stage contextualized …

Style: Improving Domain Transferability Of Asking Clarification Questions In Large Language Model Powered Conversational Agents, Yue Chen, Chen Huang, Yang Deng, Wenqiang Lei, Dingnan Jin, Jia Liu, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Equipping a conversational search engine with strategies regarding when to ask clarification questions is becoming increasingly important across various domains. Attributing to the context understanding capability of LLMs and their access to domain-specific sources of knowledge, LLM-based clarification strategies feature rapid transfer to various domains in a posthoc manner. However, they still struggle to deliver promising performance on unseen domains, struggling to achieve effective domain transferability. We take the first step to investigate this issue and existing methods tend to produce one-size-fits-all strategies across diverse domains, limiting their search effectiveness. In response, we introduce a novel method, called STYLE, to …

On The Multi-Turn Instruction Following For Conversational Web Agents, Yang Deng, Xuan Zhang, Wenxuan Zhang, Yifei Yuan, See-Kiong Ng, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Web agents powered by Large Language Models (LLMs) have demonstrated remarkable abilities in planning and executing multi-step interactions within complex web-based environments, fulfilling a wide range of web navigation tasks. Despite these advancements, the potential for LLM-powered agents to effectively engage with sequential user instructions in real-world scenarios has not been fully explored. In this work, we introduce a new task of Conversational Web Navigation, which necessitates sophisticated interactions that span multiple turns with both the users and the environment, supported by a specially developed dataset named Multi-Turn Mind2Web (MT-Mind2Web). To tackle the limited context length of LLMs and the …

Watme: Towards Lossless Watermarking Through Lexical Redundancy, Liang Chen, Yatao Bian, Yang Deng, Deng Cai, Shuaiyi Li, Peilin Zhao, Kam-Fai Wong

Research Collection School Of Computing and Information Systems

Text watermarking has emerged as a pivotal technique for identifying machine-generated text. However, existing methods often rely on arbitrary vocabulary partitioning during decoding to embed watermarks, which compromises the availability of suitable tokens and significantly degrades the quality of responses. This study assesses the impact of watermarking on different capabilities of large language models (LLMs) from a cognitive science lens. Our finding highlights a significant disparity; knowledge recall and logical reasoning are more adversely affected than language generation. These results suggest a more profound effect of watermarking on LLMs than previously understood. To address these challenges, we introduce Watermarking with …

Introduction To Programming And Applied Analytics Using Python, Matt Brown

ATU Faculty OER Books and Materials

This open electronic textbook is a collection of lecture notes, assignments, and additional background material for a junior level analytics course targeted for business students, it is free to use and copy. The text assumes readers have not had prior programming or computing courses, but have had at least one analytics course. The textbook differs from other textbooks because it serves a dual purpose, to first introduce to students the Python programming language and secondly to introduce analytics programming in Python. It is not meant to be a comprehensive book on the Python language or data analytics, rather a semester’s …

Development Of An Algorithm To Identify And Calculate The Amount Of File Slack On An Image Of A Given Drive, Nicholas Flynn

Honors Theses

As society increasingly relies on technology, the rates of cyber crime have been increasing at exponential rates. Cyber criminals are also discovering new ways to hide evidence of their crimes. This study develops a forensic analysis algorithm to evaluate the amount of file slack on an image of a drive. Slack space, leftover drive space on a disk sector after a file has been written, can be exploited to hide data. The algorithm aims to detect and calculate this slack space to help direct forensic investigations. The algorithm was evaluated on a population dataset of 100,000 files with random data …

Who Wrote The Scientific News? Improving The Discernibility Of Llms To Human-Written Scientific News, Dominik Soós

Computer Science Theses & Dissertations

Large Language Models (LLMs) have rapidly advanced the field of Natural Language Processing and become powerful tools for generating and evaluating scientific text. Although LLMs have demonstrated promising as evaluators for certain text generation tasks, there is still a gap until they are used as reliable text evaluators for general purposes. In this thesis project, I attempted to fill this gap by examining the discernibility of LLMs from human-written and LLM-generated scientific news. This research demonstrated that although it was relatively straightforward for humans to discern scientific news written by humans from scientific news generated by GPT-3.5 using basic prompts, …

Large Language Model Powered Agents For Information Retrieval, An Zhang, Yang Deng, Yankai Lin, Xu Chen, Ji-Rong Wen, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

The vital goal of information retrieval today extends beyond merely connecting users with relevant information they search for. It also aims to enrich the diversity, personalization, and interactivity of that connection, ensuring the information retrieval process is as seamless, beneficial, and supportive as possible in the global digital era. Current information retrieval systems often encounter challenges like a constrained understanding of queries, static and inflexible responses, limited personalization, and restricted interactivity. With the advent of large language models (LLMs), there's a transformative paradigm shift as we integrate LLM-powered agents into these systems. These agents bring forth crucial human capabilities like …

How Do Preservice Teachers Learn To Teach Integrated Computational Thinking?: Evidence From Planning, Enactment, And Reflection, Rachael Dektor, Samuel Severance, Kip Téllez

Journal of Computer Science Integration

This study examines pre-service teachers’ (PSTs) beliefs and understandings about computational thinking (CT) integration and lesson implementation over time. Utilizing a design-based research approach, 3 PSTs led the co-design of integrated CT lessons with support from researchers and enacted these CT integrated lessons with K-5 students. All PSTs participated in a whole-group CT workshop and engaged in one-on-one lesson design sessions with a researcher. We utilized a grounded theory approach to qualitatively analyze pre-surveys, semi-structured interviews, and video data of three PSTs enacting their lessons. We found that PSTs’ initial beliefs about CT instruction – including the importance of it …

Let’S Think Outside The Box: Exploring Leap-Of-Thought In Large Language Models With Multimodal Humor Generation, Shanshan Zhong, Zhongzhan Huang, Shanghua Gao, Wushao Wen, Liang Lin, Marinka Zitnik, Pan Zhou

Research Collection School Of Computing and Information Systems

Chain-of-Thought (CoT) [2, 3] guides large language models (LLMs) to reason step-by-step, and can motivate their logical reasoning ability. While effective for logical tasks, CoT is not conducive to creative problem-solving which often requires out-of-box thoughts and is crucial for innovation advancements. In this paper, we explore the Leap-of-Thought (LoT) abilities within LLMs — a nonsequential, creative paradigm involving strong associations and knowledge leaps. To this end, we study LLMs on the popular Oogiri game which needs participants to have good creativity and strong associative thinking for responding unexpectedly and humorously to the given image, text, or both, and thus …

Towards Faster Inference Of Transformers: Strategies For Accelerating Decoding Processes, Cunxiao Du

Dissertations and Theses Collection (Open Access)

This thesis delves into the acceleration and optimization of Transformer inference, a subject of increasing importance with the emergence of Large Language Models (LLMs). The study primarily addresses the challenges posed by two inherent properties of Transformers during inference: the quadratic complexity of the attention mechanism and the sequential nature of autoregressive inference. The research is structured into three main parts. The first part enhances the learning capabilities of non-autoregressive Transformers, achieving a remarkable 15.0x acceleration on machine translation tasks. The following section focuses on lossless acceleration through speculative decoding, where the proposed algorithm, Glide with CAPE, is shown to …

A Survey Of Practical Haskell: Parsing, Interpreting, And Testing, Parker Landon

Honors Projects

Strongly typed pure functional programming languages like Haskell have historically been confined to academia as vehicles for programming language research. While features of functional programming have greatly influenced mainstream programming languages, the imperative programming style remains pervasive in practical software development. This paper illustrates the practical utility of Haskell and pure functional programming by exploring “hson,” a scripting language for processing JSON developed in Haskell. After introducing the relevant features of Haskell to the unfamiliar reader, this paper reveals how hson leverages functional programming to implement parsing, interpreting, and testing. By showcasing how Haskell’s language features enable the creation of …

Program Analysis Of C For Conversion To Memory-Safe Rust, Dylan Cassidy

Honors Scholar Theses

C is a memory-unsafe language, which can cause software security issues. Rust is a more recent high-performance language that has memory-safe features, which motivates developers to move software to Rust. However, given the large existing C codebase, this is a tedious task, and current approaches result in memory-unsafe blocks of code remaining unsafe after conversion. We seek to use program analysis techniques to create software that identifies blocks of C code that could be safely converted to memory-safe Rust, despite using seemingly memory- unsafe access patterns. We performed manual translation of functions within the libGeoIP C library to Rust, ensuring …

Machine Learning: Face Recognition, Mohammed E. Amin

Publications and Research

This project explores the cutting-edge intersection of machine learning (ML) and face recognition (FR) technology, utilizing the OpenCV library to pioneer innovative applications in real-time security and user interface enhancement. By processing live video feeds, our system encodes visual inputs and employs advanced face recognition algorithms to accurately identify individuals from a database of photos. This integration of machine learning with OpenCV not only showcases the potential for bolstering security systems but also enriches user experiences across various technological platforms. Through a meticulous examination of unique facial features and the application of sophisticated ML algorithms and neural networks, our project …

Side Channel Detection Of Pc Rootkits Using Nonlinear Phase Space, Rebecca Clark

Poster Presentations

Cyberattacks are increasing in size and scope yearly, and the most effective and common means of attack is through malicious software executed on target devices of interest. Malware threats vary widely in terms of behavior and impact and, thus, effective methods of detection are constantly being sought from the academic research community to offset both volume and complexity. Rootkits are malware that represent a highly feared threat because they can change operating system integrity and alter otherwise normally functioning software. Although normal methods of detection that are based on signatures of known malware code are the standard line of defense, …

Enhancing Visual Grounding In Vision-Language Pre-Training With Position-Guided Text Prompts, Alex Jinpeng Wang, Pan Zhou, Mike Zheng Shou, Shuicheng Yan

Research Collection School Of Computing and Information Systems

Vision-Language Pre-Training (VLP) has demonstrated remarkable potential in aligning image and text pairs, paving the way for a wide range of cross-modal learning tasks. Nevertheless, we have observed that VLP models often fall short in terms of visual grounding and localization capabilities, which are crucial for many downstream tasks, such as visual reasoning. In response, we introduce a novel Position-guided Text Prompt ( PTP ) paradigm to bolster the visual grounding abilities of cross-modal models trained with VLP. In the VLP phase, PTP divides an image into N x N blocks and employs a widely-used object detector to identify objects …

Comparative Predictive Analysis Of Stock Performance In The Tech Sector, Asaad Sendi

LSU New Orleans Theses and Dissertations

This study compares the performance of deep learning models, including Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Transformer, in predicting stock prices across five companies (AAPL, CSCO, META, MSFT, and TSLA) from July 2019 to July 2023. Key findings reveal that GRU models generally exhibit the lowest Mean Absolute Error (MAE), indicating higher precision, particularly notable for CSCO with a remarkably low MAE. While LSTM models often show slightly higher MAE values, they outperform Transformer models in capturing broader trends and variance in stock prices, as evidenced by higher R-squared (R2) values. Transformer models generally exhibit higher MAE …

Unveiling Code Pre-Trained Models: Investigating Syntax And Semantics Capacities, Wei Ma, Shangqing Liu, Mengjie Zhao, Xiaofei Xie, Wenhang Wang, Qiang Hu, Jie Zhang, Liu Yang

Research Collection School Of Computing and Information Systems

Code models have made significant advancements in code intelligence by encoding knowledge about programming languages. While previous studies have explored the capabilities of these models in learning code syntax, there has been limited investigation on their ability to understand code semantics. Additionally, existing analyses assume the number of edges between nodes at the abstract syntax tree (AST) is related to syntax distance, and also often require transforming the high-dimensional space of deep learning models to a low-dimensional one, which may introduce inaccuracies. To study how code models represent code syntax and semantics, we conduct a comprehensive analysis of 7 code …

Plug-And-Play Policy Planner For Large Language Model Powered Dialogue Agents, Yang Deng, Wenxuan Zhang, Wai Lam, See-Kiong Ng, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Proactive dialogues serve as a practical yet challenging dialogue problem in the era of large language models (LLMs), where the dialogue policy planning is the key to improving the proactivity of LLMs. Most existing studies enable the dialogue policy planning of LLMs using various prompting schemes or iteratively enhance this capability in handling the given case with verbal AI feedback. However, these approaches are either bounded by the policy planning capability of the frozen LLMs or hard to be transferred to new cases. In this work, we introduce a new dialogue policy planning paradigm to strategize LLMs for proactive dialogue …

Large Language Models For Qualitative Research In Software Engineering: Exploring Opportunities And Challenges, Muneera Bano, Rashina Hoda, Didar Zowghi, Christoph Treude

Research Collection School Of Computing and Information Systems

The recent surge in the integration of Large Language Models (LLMs) like ChatGPT into qualitative research in software engineering, much like in other professional domains, demands a closer inspection. This vision paper seeks to explore the opportunities of using LLMs in qualitative research to address many of its legacy challenges as well as potential new concerns and pitfalls arising from the use of LLMs. We share our vision for the evolving role of the qualitative researcher in the age of LLMs and contemplate how they may utilize LLMs at various stages of their research experience.

Learning To Generate Explainable Stock Predictions Using Self‑Reflective Large Language Models, Kelvin J.L. Koa, Yunshan Ma, Ritchie Ng, Tat‑Seng Chua

Research Collection School Of Computing and Information Systems

Explaining stock predictions is generally a difficult task for traditional non-generative deep learning models, where explanations are limited to visualizing the attention weights on important texts. Today, Large Language Models (LLMs) present a solution to this problem, given their known capabilities to generate human-readable explanations for their decision-making process. However, the task of stock prediction remains challenging for LLMs, as it requires the ability to weigh the varying impacts of chaotic social texts on stock prices. The problem gets progressively harder with the introduction of the explanation component, which requires LLMs to explain verbally why certain factors are more important …

Using Pre-Trained Models For Vision-Language Understanding Tasks, Rui Cao

Dissertations and Theses Collection (Open Access)

In recent years, remarkable progress has been made in Artificial Intelligence (AI), with an increasing focus on integrating AI systems into people’s daily lives. In the context of our diverse world, research attention has shifted towards applying AI to multimodal understanding tasks. This thesis specifically addresses two key modalities, namely, vision and language, and explores Vision-Language Understanding (VLU).

In the past, addressing VLU tasks involved training distinct models from scratch using task-specific data. However, limited by the amount of training data, models may easily overfit the training data and fail to generalize. A recent breakthrough is the development of Pre-trained …

Compositional Policy Learning In Stochastic Control Systems With Formal Guarantees, Dorde Zikelic, Mathias Lechner, Abhinav Verma, Krishnendu Chatterjee, Thomas A. Henzinger

Research Collection School Of Computing and Information Systems

Reinforcement learning has shown promising results in learning neural network policies for complicated control tasks. However, the lack of formal guarantees about the behavior of such policies remains an impediment to their deployment. We propose a novel method for learning a composition of neural network policies in stochastic environments, along with a formal certificate which guarantees that a specification over the policy's behavior is satisfied with the desired probability. Unlike prior work on verifiable RL, our approach leverages the compositional nature of logical specifications provided in SPECTRL, to learn over graphs of probabilistic reach-avoid specifications. The formal guarantees are provided …

Large Language Model Powered Agents In The Web, Yang Deng, An Zhang, Yankai Lin, Xu Chen, Ji-Rong Wen, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Web applications serve as vital interfaces for users to access information, perform various tasks, and engage with content. Traditional web designs have predominantly focused on user interfaces and static experiences. With the advent of large language models (LLMs), there’s a paradigm shift as we integrate LLM-powered agents into these platforms. These agents bring forth crucial human capabilities like memory and planning to make them behave like humans in completing various tasks, effectively enhancing user engagement and offering tailored interactions in web applications. In this tutorial, we delve into the cutting-edge techniques of LLM-powered agents across various web applications, such as …

Code For Care: Hypertension Prediction In Women Aged 18-39 Years, Kruti Sheth

Electronic Theses, Projects, and Dissertations

The longstanding prevalence of hypertension, often undiagnosed, poses significant risks of severe chronic and cardiovascular complications if left untreated. This study investigated the causes and underlying risks of hypertension in females aged between 18-39 years. The research questions were: (Q1.) What factors affect the occurrence of hypertension in females aged 18-39 years? (Q2.) What machine learning algorithms are suited for effectively predicting hypertension? (Q3.) How can SHAP values be leveraged to analyze the factors from model outputs? The findings are: (Q1.) Performing Feature selection using binary classification Logistic regression algorithm reveals an array of 30 most influential factors at an …

Develop An Interactive Python Dashboard For Analyzing Ezproxy Logs, Andy Huff, Matthew Roth, Weiling Liu

Faculty and Staff Scholarship

This paper describes the development of an interactive dashboard in Python with EZproxy log data. Hopefully, this dashboard will help improve the evidence-based decision-making process in electronic resources management and explore the impact of library use.

Machine Learning-Based Gps Jamming And Spoofing Detection, Alberto Squatrito

Doctoral Dissertations and Master's Theses

The increasing reliance on Global Positioning System (GPS) technology across various sectors has exposed vulnerabilities to malicious attacks, particularly GPS jamming and spoofing. This thesis presents an analysis into detection and mitigation strategies for enhancing the resilience of GPS receivers against jamming and spoofing attacks. The research entails the development of a simulated GPS signal and a receiver model to accurately decode and extract information from simulated GPS signals. The study implements the generation of jammed and spoofed signals to emulate potential threats faced by GPS receivers in practical settings. The core innovation lies in the integration of machine learning …

Implementation Of Python Based High Voltage Tests For Gem Detectors, John Paul Hernandez

Aerospace, Physics, and Space Science Student Publications

The Compact Muon Solenoid, CMS, and other detectors at LHC are in the process of being upgraded for the HL-LHC (High-Luminosity Large Hadron Collider) which will produce more than 5 times the particle interactions than of the current LHC. One upgrade to CMS is the introduction of new GEM detectors (Gaseous Electron Multiplier), GE2/1 and ME0 shown at right are new detectors to CMS and therefore must be tested thoroughly prior to being installed.

Providing Beginners With Interactive Exploration Of Error Messages In Clojure, John Walbran, Elena Machkasova

Undergraduate Research Symposium 2024

Programmers are imperfect, and will often make mistakes when programming and create a program error, for example, attempting to divide by zero. When a computer tries to run a program with an error, the program will halt and present the details of the error to the user in the form of an error message. These error messages are often very jargon-heavy, and are not designed to be palatable to a novice programmer. This creates significant friction for new programmers trying to learn programming languages. This work is a part of an ongoing project (called Babel) led by Elena Machkasova in …

A Smart Resume Builder Tool Using Generative Ai, Ivan A. Velo Castaneda, Anas Hourani, Magdalene Moy

SACAD: Scholarly Activities

Crafting a standout resume is crucial in today’s competitive job market. Not only does it create a strong first impression on employers but it also it opens the doors for endless job opportunities. Despite existing resume assistance for FHSU students on the Career Services page, there's a lack of tools for generating or streamlining the resume writing process. To address this issue, an efficient resume builder utilizing OpenAI’s GPT-3.5 model was developed specifically for FHSU students. Its key features include intuitive template selection, dynamic AI-generated content for tailored resumes, multi-format output supporting PDF and Word formats, and a user-friendly experience …