Digital Commons Network^™

Sound Practices In Human Resources: A Critical Analysis Of How Ai Applicant Screening Tools Are Used With Deaf Individuals In The Hospitality And Tourism Sector, Sherry L. Gaynor

USF Tampa Graduate Theses and Dissertations

This study explores the intersection of Career and Workforce Education, Deaf Education, and artificial intelligence (AI) technologies used in hiring practices. The purpose of this research is to identify potential barriers to equitable employment for Deaf and Hard-of-Hearing (DHH) individuals and to propose effective methods for evaluating and assessing AI and machine learning applications utilized in recruitment and selection processes. Although AI is increasingly embedded in human resource management (HRM), there remains a significant lack of research addressing its use with special populations. In particular, no prior studies have examined how voice recognition software, facial analysis, psychometric testing, and virtual …

Effects Of Code Scaffolding In Increasing Student Confidence In Programming Cryptography, John Denny

LSU Master's Theses

Cryptography is essential for secure communications, and new threats require more students willing to program and interact with cryptographic systems. Previous research is focused on tools for teaching these systems at a high level, teaching through attacks against these systems, and proper use of these systems in software development. In this paper, we seek to design a workshop to use scaffolded Python code to teach how these cryp- tographic systems are designed. We explore the use of code scaffolding for students to program an example implementation of the McEliece crypto- graphic system to build confidence in working with these systems. …

Systematic Review Of Elementary Cybersecurity Education: Curriculum, Pedagogy, And Barriers, Na Liu, Siyu Long, Florence Martin

Journal of Cybersecurity Education, Research and Practice

Abstract -As children increasingly engage with digital platforms, the need for effective cybersecurity education has become urgent. This systematic review synthesizes 81 studies published between 2017 and 2024 to examine global curricula research focus and topics, pedagogical approaches and assessment methods, and key challenges in elementary cybersecurity education. The findings reveal six major thematic categories: student awareness, parental mediation, teacher engagement, curriculum design, community and policy support, and pedagogical innovation. Among instructional strategies, game-based learning and narrative storytelling emerge as the most frequently explored. Despite this growth, major gaps remain in curriculum consistency, teacher preparation, assessment rigor, and stakeholder coordination. …

Composition Pedagogy As Ai‑Native Coding: From Design Kit To Scholarly Framework, Daniel Plate, James Hutson

Faculty Scholarship

This article advances a field-ready framework that reconceives first-year composition as AI-native coding, translating a complete “design kit” into scholarly method, evaluative protocol, and curriculum architecture. Background: Contemporary composition pedagogy emphasizes process, genre awareness, and collaborative revision; meanwhile, modern software practice operationalizes iteration through version control, test-driven development, and continuous integration. The uploaded kit demonstrates that these cultures are isomorphic: writing stages align with SDLC phases, and automated pipelines can lint prose, execute argument “tests,” and publish artifacts with auditable histories. Approach: The study systematizes that kit into (1) a conceptual map that recasts authorship as orchestration and verification, (2) …

Do Code Semantics Help? A Comprehensive Study On Execution Trace-Based Information For Code Large Language Models, Jian Wang, Xiaofei Xie, Qiang Hu, Shangqing Liu, Yi Li

Research Collection School Of Computing and Information Systems

Code Large Language Models (Code LLMs) have opened a new era in programming with their impressive capabilities. However, recent research has revealed critical limitations in their ability to reason about runtime behavior and understand the actual functionality of programs, which poses significant challenges for their post-training and practical deployment. Specifically, Code LLMs encounter two principal issues: (1) a lack of proficiency in reasoning about program execution behavior, as they struggle to interpret what programs actually do during runtime, and (2) inconsistent and fragmented representation of semantic information, such as execution traces, across existing methods, which hinders their ability to generalize …

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 …

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 …

How Behavioral Science Can Improve The Return On Ai Investments, David De Cremer, Shane Schweitzer, Jack Mcguire, Devesh Narayanan

Research Collection Lee Kong Chian School Of Business

Many AI projects fail because leaders treat adoption as a tech purchase instead of a behavioral change problem. People resist tools that disrupt routines, overreact to visible AI errors, and prefer familiar human judgment. As a result, even good systems fail to gain purchase. Leaders can address this problem by applying “Behavioral Human-Centered AI” across the AI adoption cycle. In the design phrase, companies should co-design with diverse users, add purposeful friction where it improves scrutiny, require beta tests with subgroup results and behavioral input. During adoption, they should frame AI as an augmenter, disclose limits and safeguards, use explainability …

Seeing Culture: A Benchmark For Visual Reasoning And Grounding, Burak Satar, Zhixin Ma, Patrick Amadeus Irrawan, Wilfried Ariel Mulyawan, Jing Jiang, Ee-Peng Lim, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

Multimodal vision-language models (VLMs) have made substantial progress in various tasks that require a combined understanding of visual and textual content, particularly in cultural understanding tasks, with the emergence of new cultural datasets. However, these datasets frequently fall short of providing cultural reasoning while underrepresenting many cultures.In this paper, we introduce the Seeing Culture Benchmark (SCB), focusing on cultural reasoning with a novel approach that requires VLMs to reason on culturally rich images in two stages: i) selecting the correct visual option with multiple-choice visual question answering (VQA), and ii) segmenting the relevant cultural artifact as evidence of reasoning. Visual …

From Personas To Talks: Revisiting The Impact Of Personas On Llm-Synthesized Emotional Support Conversations, Shenghan Wu, Yimo Zhu, Wynne Hsu, Mong-Li Lee, Yang Deng

Research Collection School Of Computing and Information Systems

The rapid advancement of Large Language Models (LLMs) has revolutionized the generation of emotional support conversations (ESC), offering scalable solutions with reduced costs and enhanced data privacy. This paper explores the role of personas in the creation of ESC by LLMs. Our research utilizes established psychological frameworks to measure and infuse persona traits into LLMs, which then generate dialogues in the emotional support scenario. We conduct extensive evaluations to understand the stability of persona traits in dialogues, examining shifts in traits post-generation and their impact on dialogue quality and strategy distribution. Experimental results reveal several notable findings: 1) LLMs can …

Adasteer: Your Aligned Llm Is Inherently An Adaptive Jailbreak Defender, Weixiang Zhao, Jiahe Guo, Yulin Hu, Yang Deng, An Zhang, Xingyu Sui, Xinyang Han, Yanyan Zhao, Bing Qin, Tat-Seng Chua, Ting Liu

Research Collection School Of Computing and Information Systems

Despite extensive efforts in safety alignment, large language models (LLMs) remain vulnerable to jailbreak attacks. Activation steering offers a training-free defense method but relies on fixed steering coefficients, resulting in suboptimal protection and increased false rejections of benign inputs. To address this, we propose AdaSteer, an adaptive activation steering method that dynamically adjusts model behavior based on input characteristics. We identify two key properties: Rejection Law (R-Law), which shows that stronger steering is needed for jailbreak inputs opposing the rejection direction, and Harmfulness Law (H-Law), which differentiates adversarial and benign inputs. AdaSteer steers input representations along both the Rejection Direction …

Chain Of Strategy Optimization Makes Large Language Models Better Emotional Supporter, Weixiang Zhao, Xingyu Sui, Xinyang Han, Yang Deng, Yulin Hu, Jiahe Guo, Libo Qin, Qianyun Du, Shijin Wang, Yanyan Zhao, Bing Qin, Ting Liu

Research Collection School Of Computing and Information Systems

The growing emotional stress in modern society has increased the demand for Emotional Support Conversations (ESC). While Large Language Models (LLMs) show promise for ESC, they face two key challenges: (1) low strategy selection accuracy, and (2) preference bias, limiting their adaptability to users’ emotional needs. Existing supervised fine-tuning (SFT) struggles to address these issues, as it rigidly trains models on single gold-standard responses without modeling nuanced strategy trade-offs. To overcome these limitations, we propose a novel two-stage framework that optimizes strategy selection preferences at each dialogue turn. We first leverage Monte Carlo Tree Search to construct ESC-Pro, a high-quality …

Exploring Autonomous Agents: A Closer Look At Why They Fail When Completing Tasks, Ruofan Lu, Yichen Li, Yintong Huo

Research Collection School Of Computing and Information Systems

Autonomous agent systems powered by Large Language Models (LLMs) have demonstrated promising capabilities in automating complex tasks. However, current evaluations largely rely on success rates without systematically analyzing the interactions, communication mechanisms, and failure causes within these systems. To bridge this gap, we present a benchmark of 34 representative programmable tasks designed to rigorously assess autonomous agents. Using this benchmark, we evaluate three popular open-source agent frameworks combined with two LLM backbones, observing a task completion rate of approximately 50%. Through in-depth failure analysis, we develop a three-tier taxonomy of failure causes aligned with task phases, highlighting planning errors, task …

Envisioning Future Interactive Web Development: Editing Webpage With Natural Language, Truong Hai Dang, Jingyu Xiao, Yintong Huo

Research Collection School Of Computing and Information Systems

The evolution of web applications relies on iterative code modifications, a process that is traditionally manual and time-consuming. While Large Language Models (LLMs) can generate UI code, their ability to edit existing code from new design requirements (e.g., ”center the logo”) remains a challenge. This is largely due to the absence of large-scale, high-quality tuning data to align model performance with human expectations. In this paper, we introduce a novel, automated data generation pipeline that uses LLMs to synthesize a high-quality fine-tuning dataset for web editing, named Instruct4Edit. Our approach generates diverse instructions, applies the corresponding code modifications, and performs …

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 …

Mmlu-Prox: A Multilingual Benchmark For Advanced Large Language Model Evaluation, Weihao Xuan, Et. Al.

Research Collection School Of Computing and Information Systems

Existing large language model (LLM) evaluation benchmarks primarily focus on English, while current multilingual tasks lack parallel questions that specifically assess cross-lingual reasoning abilities. This dual limitation makes it challenging to assess LLMs’ performance in the multilingual setting comprehensively. To fill this gap, we introduce MMLU-ProX, a comprehensive benchmark covering 29 languages, built on an English benchmark. Each language version consists of 11,829 identical questions, enabling direct cross-lingual comparisons. Additionally, to meet efficient evaluation needs, we provide a lite version containing 658 questions per language. To ensure the high quality of MMLU-ProX, we employ a rigorous development process that involves …

Interaction2code: Benchmarking Mllm-Based Interactive Webpage Code Generation From Interactive Prototyping, Jingyu Xiao, Yuxuan Wan, Yintong Huo, Zixin Wang, Xinyi Xu, Wenxuan Wang, Zhiyao Xu, Yuhang Wang, Michael R. Lyu

Research Collection School Of Computing and Information Systems

Multimodal Large Language Models (MLLMs) have demonstrated remarkable performance on the design-to-code task, i.e., generating UI code from UI mock-ups. However, existing benchmarks only contain static web pages for evaluation and ignore the dynamic interaction, limiting the practicality, usability and user engagement of the generated webpages. To bridge these gaps, we present the first systematic investigation of MLLMs in generating interactive webpages. Specifically, we formulate the Interaction-to-Code task and establish the Interaction2Code benchmark, encompassing 127 unique webpages and 374 distinct interactions across 15 webpage types and 31 interaction categories. Through comprehensive experiments utilizing state-of-theart (SOTA) MLLMs, evaluated via both automatic …

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 …

Explainable Sentiment Analysis With Deepseek-R1: Performance, Efficiency, And Few-Shot Learning, Donghao Huang, Zhaoxia Wang

Research Collection School Of Computing and Information Systems

Large language models (LLMs) have transformed sentiment analysis, yet balancing accuracy, efficiency, and explainability remains a critical challenge. This study presents the first comprehensive evaluation of DeepSeek-R1—an open-source reasoning model—against OpenAI’s GPT-4o and GPT-4o-mini. We test the full 671B model and its distilled variants, systematically documenting few-shot learning curves. Our experiments show DeepSeek-R1 achieves a 91.39% F1 score on 5-class sentiment and 99.31% accuracy on binary tasks with just 5 shots, an eightfold improvement in few-shot efficiency over GPT-4o. Architecture-specific distillation effects emerge, where a 32B Qwen2.5-based model outperforms the 70B Llama-based variant by 6.69 percentage points. While its reasoning …

Generative Ai And Empirical Software Engineering: A Paradigm Shift, Christoph Treude, Margaret-Anne Storey

Research Collection School Of Computing and Information Systems

The widespread adoption of generative AI in software engineering marks a paradigm shift, offering new opportunities to design and utilize software engineering tools while influencing both developers and the artifacts they create. Traditional empirical methods in software engineering, including quantitative, qualitative, and mixed-method approaches, are well established. However, this paradigm shift introduces novel data types and redefines many concepts in the software engineering process. The roles of developers, users, agents, and researchers increasingly overlap, blurring the distinctions between these social and technical actors within the field. This paper examines how integrating AI into software engineering challenges traditional research paradigms. It …

Intentionframe: A Semi-Structured, Multi-Aspect Framework For Fine-Grained Conversational Intention Understanding, Zailong Tian, Zhuoheng Han, Lizi Liao, Lizi Liao

Research Collection School Of Computing and Information Systems

Understanding user intentions in multi-turn dialogues is critical for conversational AI, yet existing approaches—relying on rigid slot-value structures or unstructured free-text—fail to fully capture conversational complexity. In this paper, we propose IntentionFrame, a semi-structured framework inspired by psychological and cognitive intention theories, which organizes conversational intents into four interrelated aspects: situation, emotion, action, and knowledge. This design not only retains interpretability but also provides LLMs with a rich context to accurately parse and respond to nuanced user inputs. To efficiently scale IntentionFrame annotations, we introduce a Weakly-supervised Reinforced Generation (WeRG) method that leverages a small set of high-quality human annotations …

Attention Mapping For Hallucination Reduction In Arabic Financial Using Retrieval-Augmented Generation Systems, Hasan Abdulameer Hasan, Khaldoun H. Al-Hussayni, Ali Z. K. Matloob

Journal of Intelligent Informatics, Networking, and Cybersecurity

This research introduces a customized attention visualization framework for mitigating hallucinations in Arabic Retrieval-Augmented Generation (RAG) systems tailored for financial document analysis. The proposed architecture extends MarBERT with a dual-stage attention supervision mechanism and a hallucination-aware loss formulation, trained on a newly constructed dataset of 7,000 annotated Arabic financial query-context pairs. A grounding alignment score is computed over attended tokens, and generated responses are rejected when falling below a dynamically adjusted precision-aware threshold,serving as the core decision-making approach for hallucination detection. The system achieves 95.04% classification accuracy, 95.84% precision, 94.12% recall, and an F1 score of 94.97%, outperforming AraELECTRA and …

Towards Mitigation Of Hallucination For Llm-Empowered Agents: Progressive Generalization Bound Exploration And Watchdog Monitor, Siyuan Liu, Wenjing Liu, Zhiwei Xu, Xin Wang, Bo Chen, Tao Li

Michigan Tech Publications

Empowered by large language models (LLMs), intelligent agents have become a popular paradigm for interacting with open environments to facilitate AI deployment. However, hallucinations generated by LLMs - where outputs are inconsistent with facts - pose a significant challenge, undermining the credibility of intelligent agents. Only if hallucinations can be mitigated, the intelligent agents can be used in real-world without any catastrophic risk. Therefore, effective detection and mitigation of hallucinations are crucial to ensure the dependability of agents. Unfortunately, the related approaches either depend on white-box access to LLMs or fail to accurately identify hallucinations. To address the challenge posed …

Large Language Models As Information Providers For Appropriate Antimicrobial Use: Computational Text Analysis And Expert-Rated Comparison Of Chatgpt, Claude And Gemini, Marcello Di Pumpo, Maria Rosaria Gualano, Danilo Buonsenso, Francesca Raffaelli, Daniele Donà, Vittorio Maio, Patrizia Laurenti, Walter Ricciardi, Leonardo Villani

College of Population Health Faculty Papers

OBJECTIVES: Antimicrobial resistance is a critical public health threat. Large language models (LLMs) show great capability for providing health information. This study evaluates the effectiveness of LLMs in providing information on antibiotic use and infection management.

METHODS: Using a mixed-method approach, responses to healthcare expert-designed scenarios from ChatGPT 3.5, ChatGPT 4.0, Claude 2.0 and Gemini 1.0, in both Italian and English, were analysed. Computational text analysis assessed readability, lexical diversity and sentiment, while content quality was assessed by three experts via DISCERN tool.

RESULTS: 16 scenarios were developed. A total of 101 outputs and 5454 Likert-scale (1-5) scores were obtained …