Digital Commons Network^™

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 …

R2dqg: A Quality Meets Diversity Framework For Question Generation Over Knowledge Bases, Yimeng Ren, Yanhua Yu, Lizi Liao, Yuhu Shang, Kangkang Lu, Mingliang Yan

Research Collection School Of Computing and Information Systems

The task of Knowledge-Based Question Generation (KBQG) involves generating natural language questions from structured knowledge sources, posing unique challenges in balancing linguistic diversity and semantic relevance. Existing models often focus on maximizing surface-level similarity to ground-truth questions, neglecting the need for diverse syntactic forms and leading to semantic drift during generation. To overcome these challenges, we propose Refine-Reinforced Diverse Question Generation (R2DQG), a two-phase framework leveraging a generation-then-refinement paradigm. The Generator first constructs a diverse set of expressive templates using dependency parse tree similarity, capturing a wide range of syntactic patterns and styles. These templates guide the creation of question …

Advancing Molecular Graph-Text Pre-Training Via Fine-Grained Alignment, Yibo Li, Yuan Fang, Mengmei Zhang, Chuan Shi

Research Collection School Of Computing and Information Systems

Understanding molecular structure and related knowledge is crucialfor scientific research. Recent studies integrate molecular graphswith their textual descriptions to enhance molecular representationlearning. However, they focus on the whole molecular graph andneglect frequently occurring subgraphs, known as motifs, whichare essential for determining molecular properties. Without suchfine-grained knowledge, these models struggle to generalize to un-seen molecules and tasks that require motif-level insights. To bridgethis gap, we propose FineMolTex, a novel Fine-grained Moleculargraph-Text pre-training framework to jointly learn coarse-grainedmolecule-level knowledge and fine-grained motif-level knowledge.Specifically, FineMolTex consists of two pre-training tasks: a con-trastive alignment task for coarse-grained matching and a maskedmulti-modal modeling task for …

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 …

Taclr: A Scalable And Efficient Retrieval-Based Method For Industrial Product Attribute Value Identification, Yindu Su, Huike Zou, Lin Sun, Ting Zhang, Haiyang Yang, Chen Li Yu, David Lo, Qingheng Zhang, Shuguang Han, Jufeng Chen

Research Collection School Of Computing and Information Systems

Product Attribute Value Identification (PAVI) involves identifying attribute values from product profiles, a key task for improving product search, recommendation, and business analytics on e-commerce platforms. However, existing PAVI methods face critical challenges, such as inferring implicit values, handling outof-distribution (OOD) values, and producing normalized outputs. To address these limitations, we introduce Taxonomy-Aware Contrastive Learning Retrieval (TACLR), the first retrieval-based method for PAVI. TACLR formulates PAVI as an information retrieval task by encoding product profiles and candidate values into embeddings and retrieving values based on their similarity. It leverages contrastive training with taxonomy-aware hard negative sampling and employs adaptive inference …

Focus: Evaluating Pre-Trained Vision-Language Models On Underspecification Reasoning, Kankan Zhou, Yibin Lai, Kyriakos Mouratidis, Jing Jiang

Research Collection School Of Computing and Information Systems

Humans possess a remarkable ability to interpret underspecified ambiguous statements by inferring their meanings from contexts such as visual inputs. This ability, however, may not be as developed in recent pre-trained visionlanguage models (VLMs). In this paper, we introduce a novel probing dataset called FOCUS to evaluate whether state-of-the-art VLMs have this ability. FOCUS consists of underspecified sentences paired with image contexts and carefully designed probing questions. Our experiments reveal that VLMs still fall short in handling underspecification even when visual inputs that can help resolve the ambiguities are available. To further support research in underspecification, FOCUS will be released …

Evaluating And Mitigating Linguistic Discrimination In Large Language Models: Perspectives On Safety Equity And Knowledge Equity, Guoliang Dong, Haoyu Wang, Jun Sun, Xinyu Wang

Research Collection School Of Computing and Information Systems

By training on text in various languages, large language models (LLMs) typically possess multilingual support and demonstrate remarkable capabilities in solving tasks described in different languages. However, LLMs can exhibit linguistic discrimination due to the uneven distribution of training data across languages. That is, LLMs are hard to keep the consistency of responses when faced with the same task but depicted in different languages. In this study, we first explore the consistency in the LLMs’ outputs responding to queries in various languages from two aspects: safety and quality. We conduct this analysis with two datasets (AdvBench and NQ) based on …

Cami: A Counselor Agent Supporting Motivational Interviewing Through State Inference And Topic Exploration, Yizhe Yang, Palakorn Achananuparp, Heyan Huang, Jing Jiang, Phey Ling Kit, Nicholas Gabriel Lim, Cameron Shi Ern Tan, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

Conversational counselor agents have become essential tools for addressing the rising demand for scalable and accessible mental health support. This paper introduces CAMI, a novel automated counselor agent grounded in Motivational Interviewing (MI) – a client-centered counseling approach designed to address ambivalence and facilitate behavior change. CAMI employs a novel STAR framework, consisting of client’s state inference, motivation topic exploration, and response generation modules, leveraging large language models (LLMs). These components work together to evoke change talk, aligning with MI principles and improving counseling outcomes for diverse clients. We evaluate CAMI’s performance through both automated and expert evaluations, utilizing simulated …

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 …

Think Both Ways: Teacher-Student Bidirectional Reasoning Enhances Mcq Generation And Distractor Quality, Yimiao Qiu, Yang Deng, Quanming Yao, Zhimeng Zhang, Zhiang Dong, Chang Yao, Jingyuan Chen

Research Collection School Of Computing and Information Systems

Generating high-quality Multiple Choice Questions (MCQs) remains challenging for educational tools due to the need for contextual relevance and plausible distractors. Existing methods still struggle with these dual requirements, leading to questions that lack depth and distractors that are either too obvious or irrelevant. In this paper, we propose BiFlow, a novel framework that integrates bidirectional reasoning perspectives: teacher reasoning generates contextually relevant questions and plausible distractors, while student reasoning evaluates question clarity and the misleading nature of the distractors. To further enhance reasoning, we introduce PathFinder, a mechanism that employs breadth-first search and Chainof-Thought (CoT) strategies to explore diverse …

Mpo: Multilingual Safety Alignment Via Reward Gap Optimization, Weixiang Zhao, Yulin Hu, Yang Deng, Tongtong Wu, Wenxuan Zhang, Jiahe Guo, An Zhang, Yanyan Zhao, Bing Qin, Tat-Seng Chua, Ting Liu

Research Collection School Of Computing and Information Systems

Large language models (LLMs) have become increasingly central to AI applications worldwide, necessitating robust multilingual safety alignment to ensure secure deployment across diverse linguistic contexts. Existing preference learning methods for safety alignment, such as RLHF and DPO, are primarily monolingual and struggle with noisy multilingual data. To address these limitations, we introduce Multilingual reward gaP Optimization (MPO), a novel approach that leverages the well-aligned safety capabilities of the dominant language (e.g., English) to improve safety alignment across multiple languages. MPO directly minimizes the reward gap difference between the dominant language and target languages, effectively transferring safety capabilities while preserving the …

Consistent Client Simulation For Motivational Interviewing-Based Counseling, Yizhe Yang, Palakorn Achananuparp, Heyan Huang, Jing Jiang, Nicholas Gabriel Lim, Cameron Shi Ern Tan, Phey Ling Kit, Jenny Xiuhui Giam, John Pinto, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

Simulating human clients in mental health counseling is crucial for training and evaluating counselors (both human or simulated) in a scalable manner. Nevertheless, past research on client simulation did not focus on complex conversation tasks such as mental health counseling. In these tasks, the challenge is to ensure that the client’s actions (i.e., interactions with the counselor) are consistent with with its stipulated profiles and negative behavior settings. In this paper, we propose a novel framework that supports consistent client simulation for mental health counseling. Our framework tracks the mental state of a simulated client, controls its state transitions, and …

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 …

Preparing Pre-Service Teachers For Writing Instruction: Best-Practices And Insights Into Self-Efficacy, Lindsey Wiggins

Boise State University Theses and Dissertations

Many pre-service teachers (PSTs) report feeling under-prepared to teach writing, a challenge often linked to limited attention to writing instruction in teacher preparation programs (TPPs). While writing methods courses offer opportunities to build PSTs’ self-efficacy and pedagogical skill, questions remain about how to best structure these experiences and measure their impact. This three-article dissertation examines how PSTs develop self-efficacy for writing and writing instruction during teacher preparation and how those beliefs relate to instructional practices.

In Study I, I conducted a systematic literature review to examine how researchers measure the effects of effective writing and writing instruction interventions with elementary …

The Impact Of Culture And Language On Internal Communication And Patient Care In Small To Medium-Sized Black Immigrant-Owned Healthcare Practices In Texas., Chisom Nwosu

Dissertations

This qualitative phenomenological study explored how cultural competency in small to medium-sized Black immigrant-owned healthcare practices in Texas affects internal communication and patient care. Through semi-structured interviews with nine clinical and administrative leaders in Dallas and Houston, five themes emerged: culturally competent leadership, intentional communication structures, language and interpretation practices, patient-centered cultural sensitivity, and the use of technology for adaptation. Findings suggest that culturally aware leadership and inclusive communication strategies foster team cohesion and improve patient trust and care. Participants reported adapting workflows to meet religious, language, and communication needs through human and technological tools. The study underscores embedding cultural …

Reflections Of Linguistic Experiences In A Borderland: Influences On Cultural Identity And Teacher Praxis, Iliana Cantu

Theses and Dissertations

This Autoethnographic dissertation uses autohistoria-teoria to critically analyze my lived curriculum as a Mexican-born raised in the borderland of the Rio Grande Valley. This research aims to understand the influence of my linguistic experiences on my cultural identity and teaching praxis within the same context. Drawing from Anzaldua’s (1987) concept of Borderlands as a contextual lens and Raciolinguistics as a theoretical framework, I examine and reflect on key linguistic experiences that have perpetuated colonizing linguistic practices rather than fostered linguistic diversity. Additionally, Culturally Linguistic Sustaining Pedagogy serves as a framework to critically analyze my teaching praxis in relation to my …

Barriers To Hispanic Post-Secondary Education In Science Fields, Luis Slayton

Theses and Dissertations

The study aimed to examine whether external barriers could be identified and are present throughout a Hispanic individual's educational life. The beliefs of the Hispanic community regarding education and the nature of acquiring an education could be relevant to the factors that impede the completion of high school. A survey approach was chosen as the methodology for the study due to the confidential nature of a questionnaire. Human nature tends to be more honest when not asked personal questions face-to-face. Additionally, there is potential to generalize attributes from a small sample to a larger population, allowing inferences about the identified …

Using Equivalence-Based Instruction And Behavioral Skills Training To Teach Social Skills, Alexander Orzeck

Theses

Social skills are an integral part of human life, so it stands to reason that teaching methodologies should be developed to instruct people in this complex topic. One method to teach social skills has been behavioral skills training, in which the four-step sequence of vocal and written instruction, modeling, roleplay, and feedback exposes learners to the social concepts until a mastery criterion is reached. Skills relevant to socialization have also been taught with equivalence-based instruction, in which the concept of stimulus equivalence is employed to generate novel relations between stimuli for the purpose of teaching some skill. No instance was …

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) …

Projecting Echoes: Valeria Luiselli's Writing On Immigration, Jacob C. Cisneros

Electronic Theses, Projects, and Dissertations

The growing concerns of immigration has been a fraught topic in both U.S. society and the American political landscape. Certain political narratives are formed which fuel the debate for and against immigration. This coincides with how immigrants are treated and how legal processes change throughout each term of presidency within the United States. This has sparked outrage from both advocates and adversaries of immigrants coming into the United States. Papers, speeches, news articles, and more have been created from both sides of the argument concerning how to handle the immigration crisis along with the question of how immigrants and asylum …

Deaf Faculty Members’ Experiences In Higher Education Institutions, Stephanie Proctor Horvath

Electronic Theses and Dissertations

Deaf faculty members bring diverse perspectives to higher education, yet their experiences remain underexplored in academic research. The critical first year of teaching can shape their career experiences, revealing both opportunities for growth and systemic barriers. The purpose of this study was to understand deaf faculty members’ experiences, focusing on their transition into academic roles, the accommodations provided in their workplaces, and the challenges they faced. This study employed a qualitative phenomenological design, utilizing semi-structured interviews with 15 Deaf faculty members, whose teaching experience ranges from 1 to 30 years. In the reflexive thematic analysis and AI-coding of this data, …

Computational Fact-Checking With Limited Resources, Fengzhu Zeng

Dissertations and Theses Collection (Open Access)

The rapid dissemination of information through online platforms has sparked widespread concern about the propagation of misinformation. Manual fact-checking by pro- fessional fact-checkers is time-consuming and lacks scalability to address the vast volume of daily information. Consequently, computational fact-checking, driven by automated techniques in natural language processing (NLP), has garnered interest as
a potential solution. However, computational fact-checking faces critical challenges limited resources, particularly due to the issues of data scarcity and computing resource constraints. One key challenge is data scarcity, which arises from the constant generation of new information and emerging events on social media. This scarcity manifests in …

Promoting Understanding Of Soft Power Theory : A Case Study Of Confucius Institutes Along The Belt And Road, Dan Yang

Lingnan Theses (Doctoral degree)

This dissertation explores the function of Confucius Institutes (CI) as key tools within China’s soft power approach, particularly in the framework of the Belt and Road Initiative (BRI). It provides a detailed and empirically based analysis of how these institutes operate within various national contexts. Drawing upon Joseph Nye’s soft power theory and supported by literature on public diplomacy, this study assesses the ways in which CIs translate cultural, linguistic, and educational assets into international influence. Despite the rapid expansion of CIs globally, their actual effectiveness in achieving cultural diplomacy and tangible soft power outcomes remains uncertain. Advocates emphasize the …

Socioeconomic Status Shapes Dyadic Interactions: Examining Behavioral And Physiologic Responses, Jacinth J. X. Tan, Tessa V. West, Wendy B. Mendes

Research Collection School of Social Sciences

With more opportunities for diverse interactions, little is known about how social interactions involving people of different socioeconomic status (SES) may unfold. We investigated social attunement patterns in dyadic interactions involving SES. Unacquainted individuals recruited from the community interacted with similar-or-different-SES partners in the lab (Ndyads = 130). Attunement was assessed throughout the interaction by examining physiological linkage—how much a person’s physiological change is predicted by another’s physiological change, over time. Overall, low-SES participants showed stronger physiological linkage—indicating greater attunement—to partners across SES. Participants also appeared more comfortable when interacting with low-SES partners. There were no SES differences in dominance …

Language Brokering Conditions The Indirect Association Between Mexican‐Origin Adolescents’ Academic Discrimination And Educational Expectations, Su Yeong Kim, Yayu Du, Chantal Alvarado, Wei Xiang Sim, Wen Wen, Tianlu Zhang, Jingyi Shen

Research Collection School of Social Sciences

Mexican‐origin adolescents, a significant portion of the US Latino population, often experience a decline in educational expectations from early to late adolescence. Contextual factors such as academic discrimination and language brokering for parents may contribute to this decline. This study investigates the indirect effect of academic discrimination experienced in middle school on educational expectations in young adulthood through high school grades and engagement, and the moderating role of language brokering experiences in these relations. Data were collected from 604 Mexican‐origin adolescents across four waves from 2012 to 2023. Academic discrimination experiences in middle school were negatively associated with school grades …

Designing Multilingual (Maker) Spaces: Exploring The Intersections Of Play, Posthumanism, And Pre-Kindergarten, Victoria G. Pennington

All Dissertations

In this dissertation, I explore the posthuman play literacies of multilingual makerspaces with four-year-olds, emphasizing the need for such a study while situating my arguments within the existing literature and outlining my methodological approach. Chapter One critiques the public 4-year-old kindergarten systems, arguing institutionalized cultural and linguistic ideologies restrict multilingual learners’ (MLs) opportunities for meaning-making. I draw on the raciolinguistic perspective (Flores & Rosa, 2015) and its intersection with a posthumanist paradigm (Braidotti, 2013), framing my research questions as lines of inquiry to guide the study. Key posthumanist literacies concepts are defined, highlighting the entanglement of literacies, discourses, materials, and …

More Than Numbers: Interrogating The Instructional Capacity Of Middle School Mathematics Teachers, Yashica R. Latimer

All Dissertations

This study examines how middle school mathematics teachers conceptualize and enact culturally responsive mathematics teaching (CRMT) within a district-supported professional learning initiative. Guided by the CRMT framework developed by Aguirre and Zavala (2013), the research explores how instructional decision-making intersects with equity-focused pedagogy.

Two central questions inform the study: (1) How do middle school mathematics teachers interpret and apply CRMT principles in their classroom practice? (2) What specific instructional strategies do teachers use to integrate cultural responsiveness into their instruction?

Using a qualitative multiple-case study design, data were collected from three teachers participating in a professional learning group called MORE …

Increasing Student Enrollment In The Dual-Language Mandarin Immersion Program: Leveraging Marketing And Outreach Within A Strategic Enrollment Management Framework, Na Zhang

All Dissertations

This study examines the impact of marketing and outreach strategies on enhancing family awareness and increasing enrollment in a Dual-Language Mandarin Immersion (DLMI) program in South Carolina. The history of bilingual education has shown an increased interest in recent decades. At the same time, Mandarin immersion programs continue to face challenges and under-enrollment. This study employs a mixed-methods design to collect data from surveys and interviews with parents of children entering kindergarten. The data collection also includes interviews with Mandarin Immersion teachers and attending community events. The purpose is to identify effective practices and ongoing barriers to enrollment. Informed by …