Digital Commons Network^™

Reading The Word And The World: Overstanding Literacy In Aboriginal And Chinese Classrooms, Gui Ying Annie Yang-Heim

Faculty Publications - College of Education

This qualitative comparative case study examines how culturally grounded philosophies of education shape the teaching and learning of reading in two cross-cultural contexts—an Aboriginal Australian classroom and urban Chinese elementary schools. Drawing on interpretive and reflexive methodologies, it investigates how Aboriginal and Confucian epistemologies influence literacy practices and how these practices align with or resist dominant, decontextualized models of reading instruction. Data sources include classroom observations, reading assessments, teacher interviews, and researcher reflections. Conceptually framed by Gadamer’s hermeneutics, Bourdieu’s theory of cultural capital, Habermas’s typology of knowledge, and the Caribbean concept of overstanding, this research finds that Aboriginal literacy is …

The Root Cause Of Perceived Appraisal Politics Using Evidence From The South Korean Public Sector, Jinwoong Yoo, Saeyeon Roh, Mohamed Haddoud, Smita Tripathi

Plymouth Business School

The purpose of this study is to investigate the root causes of Perceived Appraisal Politics (PAP) within the public sector in South Korea. Scholars in the field of Human Resource Management (HRM) have identified the determinants of PAP in an effort to mitigate it. However, the complex interactions among those determinants and root causes have been overlooked. Therefore, we adopt a novel methodology in this study that combines Interpretive Structural Modelling (ISM) and fuzzy-Decision-Making Trial and Evaluation Laboratory (f-DEMATEL). The findings indicate that the root causes of PAP include the presence of cliques, ambiguity of appraisal policies and goal ambiguity …

Effectiveness Of Ai-Powered Language Learning Tools In The Workplace, Iswariya Baskar

Electronic Theses and Dissertations

This dissertation explored the experiences of multilingual employees with AI-powered language learning tools in financial and technology firms across the United States. As multilingual communication becomes increasingly vital in the workplace, the integration of artificial intelligence (AI) offers promising support in language acquisition and cross-cultural collaboration. The purpose of this basic qualitative study was to explore how AI-powered language learning tools influence the acquisition and retention of foreign languages of employees within financial and technology firms, how these tools strengthen professional identity and interpersonal communication, and how code-switching facilitated by AI impacts user experience and workplace engagement. Drawing from the …

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 …

The Irrelevance Of “Peak Fame” On Celebrity Candidate Success, Richard T. Longoria, Dana Reyes

Political Science Faculty Publications

Objective

Does it matter “when” a celebrity runs for office? The political scientists who study celebrity candidates need to consider an important insight from communications and media scholars. Fame is a time-dependent variable. Someone who was famous 40 years ago may no longer be widely known today.

Methods

A list of celebrity political candidates who ran for office in the United States between 1865 and 2022 was created to measure campaign success.

Results

In terms of winning an election, it does not matter whether a celebrity candidate runs at the peak of their fame or waits until decades later. What …

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. …

Discussion Of "Csr And Negative Corporate Events: The Moderating Role Of Managerial Overconfidence", Hye Sun Chang

Research Collection School Of Accountancy

Corporate social responsibility (CSR) refers to the notion that firms are accountable not only to shareholders but also to a broader set of stakeholders including customers, employees, creditors, and the communities in which they operate. Although CSR has long been part of corporate discourse, its prominence has grown with the rise of environmental, social, and governance (ESG) concerns. Today’s consumers and stakeholders are increasingly attentive to issues such as climate change, economic inequality, labor rights, and social justice, prompting firms to align their strategies with evolving societal expectations. Building on this increasingly salient backdrop, Chu et al. (2026), hereafter CCT, …

Spanish Heritage Speakers And Latinidad: How Spanish Fluency Influences Self-Perceived Latinidad Among Heritage Speakers, David Alejandro Rivera Sandoval, Gladys Valle

Undergraduate Theses and Capstone Projects

Abstract of Research: This study examines 1) how heritage speakers' self-perceived proficiency and fluency in Spanish influence their identity as Latinos, and 2) the generational similarities and differences in their lived experiences. Through surveys and interviews, the relationship between Spanish proficiency and fluency and perceived Latinidad among nine Spanish heritage speakers (with Latin American ancestry) has been assessed. The research suggests that no statistically significant relationship was found between language proficiency or fluency and perceived Latinismo. However, qualitative findings revealed that participants construct their Latino identity based on cultural values, lived experiences, and a sense of belonging rather than language …

Educate, Elevate, Empower: Shaping Future-Ready Teachers For Superdiverse Classrooms, Abdelhamid Helmy Safa

Research outputs 2022 to 2026

This paper critically examines the transformative potential of integrating Community Engagement (CE) and Culturally Responsive Pedagogy (CRP) within Initial Teacher Education (ITE) programs globally. It highlights the significance of community-based learning and the Funds of Knowledge (FoK) framework in preparing educators to address the complexities of superdiverse classrooms. Through a systematic review, the study identifies effective practices and systemic barriers in ITE, advocating for a paradigm shift that aligns teacher preparation with the cultural realities of students. The proposed model synthesizes CRP, CE, and FoK to cultivate critical consciousness and adaptive expertise, essential for fostering inclusive learning environments. By providing …

Empowering Community Health Workers In Dementia Care In South Texas, Stephanie Santiago-Mejias, Shanae L. Rhodes, Fayron R. Epps, Robin C. Hilsabeck, Noe Garza, Sudha Seshadri, Neela K. Patel

School of Medicine Publications

Alzheimer's disease and related dementias disproportionately affect minority racial and ethnic communities. Community health workers are essential in addressing these disparities. We evaluated the impact of an educational workshop focusing on improving knowledge and preparedness in dementia care. Sixty-one CHWs attended in-person sessions in Texas and completed surveys to measure confidence and plans to apply the knowledge gained. Results revealed a significant increase in confidence in providing dementia care post-training (p < 0.001). Qualitative analysis identified five primary roles of CHWs. These findings demonstrate the potential of training interventions to improve knowledge gaps and empower CHWs to address dementia in underserved communities.

Recommendations From Multi-Disciplinary Professionals For Survivor-Informed And Comprehensive Care For Human Trafficking Survivors, Christina Tsoi, Timothy B. Smith, Elizabeth Cutrer-Párraga, Devan Clayton, Joshua M. Marshall, Jamila Mastny

Faculty Publications

Background: Human trafficking affects millions of people worldwide with multiple adverse outcomes including psychopathology. Although research on human trafficking has become abundant in other academic disciplines (e.g., public health, criminology, social work), healthcare research specific to the mental health treatment of survivors remains limited. Objective: The purpose of this study was to gather recommendations from professionals about mental health treatment of trafficking survivors. Method: Semi-structured interviews were conducted with 21 multidisciplinary professionals working with trafficking survivors. Data were analyzed using qualitative content analysis methodology. Results: An overarching theme derived from the data concerned the recommendation to implement trafficking survivor-informed care, …

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 …

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 …

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 …

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 …

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 …

Assessing Teachers’ Practices In Supporting Gifted/Talented And Twice-Exceptional Students In Schools And Centers In Abu Dhabi, Zayed Jaber

Theses

Gifted/talented and twice-exceptional (2e) students, especially those whose needs are often overlooked in mainstream classrooms, are more likely to benefit from consistently implemented Differentiated Instructional Practices (DIPs). This study aimed to examine implelemntation of DIPs for gifted/talented and 2e students and to compare the practices implemented between of Special Educational Needs (SEN) teachers and General Education teachers in schools and centers within Abu Dhabi. This research used a quantitative, cross-sectional survey design to collect data from eighty-six teachers from Abu Dhabi. A questionnaire was designed to rate teachers’ self-reported implementation of DIPs across the four domains of content, process, product, …

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 …

How Do Emirati University Students Develop Their Academic Biliteracy? A Mixed-Method Study, Eman Kamel Rababa

Dissertations

Framed by Hornberger’s continua of biliteracy model, this study investigated the developmental dynamics of academic biliteracy among Emirati university students. The research employed a sequential mixed-methods design, conducted across three public universities in the UAE. In the initial qualitative phase, interview data were collected from 30 students. Informed by these findings and the extant literature, a quantitative survey was then developed and administered to a sample of 299 students from various disciplines. The qualitative data were analyzed using reflexive thematic analysis, while the quantitative data were examined using advanced statistical analyses, including structural equation modeling. Three primary themes emerged from …

The Port Of Mombasa As A Potential Green Hydrogen Hub : A Techno-Economic Feasibility Study, Rose Mbula Mutevu

World Maritime University Dissertations

No abstract provided.

It Hurts To Become, Ana Maria Joyce

Theses

Using the medium of oil painting, this thesis will investigate the ways that memories of my past inform and distort my perception of reality. Using domestic spaces as a framework in combination with my own body as the subject matter, I am creating compositions that redefine the meaning of home as a concept. Rather than a physical place of comfort, home is a cemetery for past selves that I revisit in my mind and grieve, no matter the time that has passed. By expressing this internal decay through physically scraping and sludging paint onto large scale surfaces, I aim to …

Beyond Autonomy: Rethinking Deception In Sexual Assault Law, Marie Manikis

Vanderbilt Law Review

This Article focuses on recent developments in Britain in which courts have recognised gender deception as a sexual assault by using an autonomy based argument to define deception/fraud that vitiates consent in sexual offences. This Article argues against the defensibility of a framework that criminalizes deception on the basis of an ill defined autonomist based understanding as opposed to a more restrictive standard. It proposes that any adopted standard should incorporate social context and be reflexive of the ways that the state has contributed to these contexts, namely the social conditions under which the deceit takes place as well as …