Digital Commons Network^™

Faithfulrag: Fact-Level Conflict Modeling For Context-Faithful Retrieval-Augmented Generation, Qinggang Zhang, Zhishang Xiang, Yilin Xiao, Le Wang, Junhui Li, Xinrun Wang, Jinsong Su

Research Collection School Of Computing and Information Systems

Large language models (LLMs) augmented with retrieval systems have demonstrated significant potential in handling knowledge-intensive tasks. However, these models often struggle with unfaithfulness issues, generating outputs that either ignore the retrieved context or inconsistently blend it with the LLM’s parametric knowledge. This issue is particularly severe in cases of knowledge conflict, where the retrieved context conflicts with the model’s parametric knowledge. While existing faithful RAG approaches enforce strict context adherence through well-designed prompts or modified decoding strategies, our analysis reveals a critical limitation: they achieve faithfulness by forcibly suppressing the model’s parametric knowledge, which undermines the model’s internal knowledge structure …

Causalabstain: Enhancing Multilingual Llms With Causal Reasoning For Trustworthy Abstention, Yuxi Sun, Aoqi Zuo, Wei Gao, Jing Ma

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) often exhibit knowledge disparities across languages. Encouraging LLMs to abstain when faced with knowledge gaps is a promising strategy to reduce hallucinations in multilingual settings. Current abstention strategies for multilingual scenarios primarily rely on generating feedback in various languages using LLMs and performing self-reflection. However, these methods can be adversely impacted by inaccuracies and biases in the generated feedback. To address this, from a causal perspective, we introduce CausalAbstain, a method that helps LLMs determine whether to utilize multiple generated feedback responses and how to identify the most useful ones. Extensive experiments demonstrate that CausalAbstain effectively …

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 …

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 …

L3net: Localized And Layered Reparameterization For Incremental Learning, Xuandi Luo, Huaidong Zhang, Yi Xie, Hongrui Zhang, Xuemiao Xu, Shengfeng He

Research Collection School Of Computing and Information Systems

Model-based class incremental learning (CIL) methods aim to address the challenge of catastrophic forgetting by retaining certain parameters and expanding the model architecture. However, retaining too many parameters can lead to an overly complex model, increasing inference overhead. Additionally, compressing these parameters to reduce the model size can result in performance degradation. To tackle these challenges, we propose a novel three-stage CIL framework called Localized and Layered Reparameterization for Incremental Learning (L3Net). The rationale behind our approach is to balance model complexity and performance by selectively expanding and optimizing critical components. Specifically, the framework introduces a Localized Dual-path Expansion structure, …

Preface, Special Issue For The 16th International Conference On Graph Transformation (Icgt 2023), Maribel Fernández, Christopher M. Poskitt

Research Collection School Of Computing and Information Systems

This special issue contains six extended versions of papers presented at the 16th International Conference on Graph Transformation (ICGT 2023), held in Leicester, UK, on 19–20 July 2023. The conference was part of STAF 2023 (Software Technologies: Applications and Foundations) and was held under the auspices of the European Association for Theoretical Computer Science (EATCS), the European Association of Software Science and Technology (EASST), and the IFIP Working Group 1.3, Foundations of Systems Specification.

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 …

Towards Context-Aware Traffic Classification Via Time-Wavelet Fusion Network, Ziming Zhao, Zhuoxue Song, Xiaofei Xie, Zhaoxuan Li, Jiongchi Yu, Fan Terry Zhang, Tingting Li

Research Collection School Of Computing and Information Systems

Encrypted traffic classification occupies a significant role in cybersecurity and network management. The existing encrypted traffic classification technology mostly relies on intra-flow semantics for extracting features. However, considering that some attack behaviors inherently have similar patterns to legitimate behaviors, and powerful adversaries could simulate benign users to conceal their attack intentions, intra-flow features may be similar between different categories. In this paper, we propose TrafficScope, a time-wavelet fusion network based on Transformer to enhance the performance of encrypted traffic classification. Specifically, in addition to using intra-flow semantics, TrafficScope also extracts contextual information to construct more comprehensive representations. Moreover, to cope …

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 …

Assessing The Robustness Of Test Selection Methods For Deep Neural Networks, Qiang Hu, Yuejun Guo, Xiaofei Xie, Maxime Cordy, Wei Ma, Mike Papadakis, Lei Ma, Yves Le Traon

Research Collection School Of Computing and Information Systems

Regularly testing deep learning-powered systems on newly collected data is critical to ensure their reliability, robustness, and efficacy in real-world applications. This process is demanding due to the significant time and human effort required for labeling new data. While test selection methods alleviate manual labor by labeling and evaluating only a subset of data while meeting testing criteria, we observe that such methods with reported promising results are simply evaluated, e.g., testing on original test data. The question arises: are they always reliable? In this article, we explore when and to what extent test selection methods fail. First, we identify …

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 …

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 …

Comparative Nitrene-Transfer Chemistry To Olefins Mediated By First-Row Transition Metal Catalysts Supported By A Pyridinophane Macrocycle With N4 Ligation, Himanshu Bhatia, Lillian P. Adams, Ingrid Cordsiemon, Suraj Kumar Sahoo, Amitava Choudhury, Thomas R. Cundari, Pericles Stavropoulos

Chemistry Faculty Research & Creative Works

A 12-membered pyridinophane scaffold containing two pyridine and two tertiary amine residues is examined as a prototype ligand (^tBuN4) for supporting nitrene transfer to olefins. The known [(^tBuN4)M^II(MeCN)2]²⁺ (M = Mn, Fe, Co, and Ni) and [(^tBuN4)Cu^I(MeCN)]⁺ cations are synthesized with the hexafluorophosphate counteranion. The aziridination of para-substituted styrenes with PhI=NTs (Ts = tosyl) in various solvents proved to be high yielding for the Cu(I) and Cu(II) reagents, in contrast to the modest efficacy of all other metals. For α-substituted styrenes, aziridination is accompanied by products of aziridine …

Visceral, Neural, And Immunotoxicity Of Per- And Polyfluoroalkyl Substances: A Mini Review, Pietro Martano, Samira Mahdi, Tong Zhou, Yasmin Barazandegan, Rebecca Iha, Hannah Do, Joel Burken, Paul Ki-Souk Nam, Qingbo Yang, Ruipu Mu

Chemistry Faculty Research & Creative Works

Per- and polyfluoroalkyl substances (PFASs) have gained significant attention due to their widespread distribution in the environment and potential adverse health effects. While ingestion, especially through contaminated drinking water, is considered the primary route of human exposure, recent research suggests that other pathways, such as inhalation and dermal absorption, also play a significant role. This review provides a concise overview of the toxicological impacts of both legacy and emerging PFASs, such as GenX and perfluoro butane sulfonic acid (PFBS), with a particular focus on their effects on the liver, kidneys, and immune and nervous systems, based on findings from recent …

Exploring Rehabilitation Therapists' Knowledge And Perspectives On The Use Of Artificial Intelligence And Machine Learning For Persons Poststroke, Hannah Clark, Mia Delvecchio, Min Hun Lee, Elena D. Brown, Kaia Mikula, Robert Halyama, Kasey Stepansky

Research Collection School Of Computing and Information Systems

Research Objectives: The use of technology such as robotics, gaming systems, self-monitoring apps, or other sensor-based devices in standard practice is infrequent. Due to the rapid development of artificial intelligence (AI) and machine learning (ML) applications, it is important to look at how therapists perceive AI/ML, and design applications with potential barriers in mind. to support future integration into practice. The purpose of this research project is to gain rehabilitation therapists’ perspectives on AI/ML in post-stroke assessment and intervention.Design: This ongoing study uses a mixed methods design with surveys and focus groups. Participants engaged in a 30-minute webinar to learn …

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 …

Bridging The Gap: Evaluating The Effectiveness Of Trio Student Support Services In Promoting Retention, Persistence, And Graduation At Boise State University, Ryan Brevik

Boise State University Theses and Dissertations

This dissertation examines the effectiveness of TRIO Student Support Services (SSS) programs at Boise State University in promoting academic success of first-generation college students, students from financially limited backgrounds, and students with documented disabilities. Using a quantitative, quasi-experimental design, a secondary data analysis was completed to compare fall-to-fall retention rates, four-year graduation rates, and six-year graduation rates between TRIO SSS participants and a matched comparison group of non-participants with similar demographic and academic characteristics. Grounded in the theoretical frameworks of Appreciative Advising, self-efficacy theory, sense of belonging, student involvement theory, and student persistence models, this study adds to the existing …

Integration Of Highly Mismatched Iii-Sb Virtual Substrates On Silicon Via Interfacial Misfit Arrays For Short-, Mid-, And Long-Wave Infrared Applications, Trent Garrett

Boise State University Theses and Dissertations

Lattice constants of the III-V semiconductors range from 5.45 Å (GaP) to 6.48 Å (InSb). III-V semiconductors are grown on commercially available substrates made from binary III-V materials (e.g., GaAs, InP, and GaSb), or group IV materials (e.g., Si or Ge). These substrates offer very high quality, but only offer access to a small number of specific lattice constants. Given this constraint, it is desirable to develop growth methods that would allow the grower to modulate from the substrate lattice constant into the lattice constant of the material structure under investigation.

Device structures made from III-V semiconductors lattice-mismatched to these …

Failure Study Of Silicon Gated Field Emitter Arrays: Experiment And Simulation, Rushmita Bhattacharjee

Boise State University Theses and Dissertations

Silicon-based Gated Field Emitter Arrays (Si-GFEAs) are among the most well-developed field emitters. They are being actively explored for vacuum transistors and microwave vacuum electron devices due to their high-frequency performance, radiation resistance, and thermal stability up to 400 °C. However, their long-term reliability is limited by sudden failure events, resulting in cathodic vacuum arcs. This dissertation presents a combined experimental and simulation-based investigation into arc initiation mechanisms in Si-GFEAs. Different device arrays were tested under normal operation in vacuum at 10^-7 Torr with gate voltages of 50-70 V and emission currents from tens of nA to tens of µA. …

If Alcohol Consumption Were Eliminated, Which Us Counties Would Still Experience High Rates Of Breast Cancer Among Women?, Hina Javed

Boise State University Theses and Dissertations

Background

Breast cancer is the most prevalent cancer among women in the United States, accounting for roughly one-third of all newly diagnosed female cancers (American Cancer Society, 2024). The risk factors for breast cancer include both non-modifiable and modifiable factors. Non-modifiable factors include age at menarche, early menstrual cycles and late menopause. Modifiable factors include smoking, diabetes, obesity and environmental factors such as air pollution. The interplay between lifestyle factors and environmental exposures in cancer development has long been debated. While alcohol consumption is widely recognized as a major breast cancer risk factor, the role of environmental exposure such as …

Changes In Co-Activation And Lower Limb Stiffness During Prolonged Load Carriage, Matthew V. Robinett

Boise State University Theses and Dissertations

Introduction: Overuse musculoskeletal injuries are a common, costly challenge for the armed services. A stiffer lower limb during routine prolonged load carriage tasks may be necessary to attenuate elevated ground reaction forces but further increases musculoskeletal overuse injury risk. Quantifying leg and joint stiffness provides comprehensive and joint level insight into the attenuation of ground reaction forces, and subsequent injury risk. But, it is currently unknown how prolonged load carriage affects leg, knee and ankle stiffness, and knee and ankle muscular activation. Purpose: This study sought to quantify leg, knee, and ankle stiffness, and the activation and coordination of associated …

The Role Of Managerial Support In Influencing The Attitudes Of Highly Educated Millennials In Serbia, Dimitrije Gasic, Vladimir Dzenopoljac, Mladen Cudanov, Jozsef Poor, Nemanja Berber

All Works

This study explores the influence of managerial support on the attitudes of highly educated (BSc, MSc, and PhD) millennials in Serbia, focusing on job satisfaction, turnover intention, and job stress. Understanding this relationship is crucial for enhancing employee retention and organisational efficiency given the evolving workplace dynamics. Managerial support, encompassing emotional, instrumental, and informational assistance, is hypothesised to positively impact job satisfaction while reducing turnover intention and job stress. Data were collected through an online survey from 367 respondents in two waves (the first wave in January 2024 and the second in July 2024) and analysed using partial least squares …

Artificial Intelligence Integration And Teachers' Self-Efficacy In Physics Classrooms, Fouad Yehya, Areej Elsayary, Ghadah Al Murshidi, Ahmed Al Zaabi

All Works

The United Arab Emirates (UAE), in its vision 2021 and the UAE centennial 2071 plan, highlights the essential role of artificial intelligence (AI) and technology in shaping a knowledge-based, future-ready society. This study explores the integration of AI in physics classrooms, focusing on secondary education in the UAE. It also investigates the perceptions and self-efficacy of physics teachers regarding the use of AI tools in classroom settings. A qualitative research design was employed to gather in-depth insights from 15 physics teachers across schools in Sharjah, assessing their confidence and readiness for AI integration through the lens of the attitude and …

Youth Attitudes Towards The Effects Of Social Media Addiction A Study On University Students In The United Arab Emirates, Fokiya Akhtar, Fawzia Abdulla Alali

All Works

Objectives: This study aims to understand youth’s attitudes toward the effects of social media usage and its risk factors. It also investigates the impact of social media addiction on youth, and determines the mediating factors in this relationship, such as ‘FOMO’ (fear of missing out) and nocturnal social media usage. Methods :For the purpose of this research, 327 university students were surveyed using the Social Media Addiction Scale, the FOMO Scale, the Nocturnal Social Media Use Scale, and the Pittsburgh Sleep Index Scale. Results: The results reveal statistically significant correlations between high social media usage and adverse effects on mental …

Psilocybin And Death Anxiety: A Dual-Mechanism Approach To Existential Distress, Annabelle Swain

University Honors Theses

This literature review looks at how psilocybin, the active compound in "magic mushrooms," can help people deal with death anxiety; the deep fear of dying or losing control that shows up in lots of mental health struggles. While traditional treatments like SSRIs and talk therapy work for some people, they don't always get to the root of the problem. Psilocybin works differently. It changes brain activity, especially in networks tied to repetitive, self-focused thinking, as well as creates powerful, emotional experiences that help people rethink how they see life and death. This paper covers recent research showing how one or …

Analysis Of The Clinical, Socioeconomic, And Sociodemographic Characteristics Of Virally Unsuppressed Children Aged 2-14 Living With Hiv/Aids In The Region Of Abidjan 2 – Côte D’Ivoire (Region Supported By Usaid), Maman Fathim Kamagate

Capstone Experience: Master of Public Health

Background: Viral suppression among children living with HIV (CLHIV) remains suboptimal in Côte d’Ivoire. This study assessed clinical, socioeconomic, and demographic characteristics associated with viral non-suppression among CLHIV aged 2–14 years in Abidjan 2 to inform targeted interventions under the U.S. Agency for International Development (USAID)-supported Reaching Impact, Saturation, and Epidemic Control (RISE) project.

Methods: A retrospective analysis was conducted using routine program data from 1,203 CLHIV across 73 health facilities. Descriptive, bivariate, and multivariate analyses were performed to examine associations with viral load suppression status. Findings guided the development of a multi-level implementation plan using Kotter’s Change Management Framework, …

Perceived Obligations Of Older Partners In Living-Apart Together Relationships, Allison M. Martin

Human Development and Family Sciences Undergraduate Honors Theses

Older and middle-aged adults are increasingly in Living-Apart-Together (LAT) relationships characterized by committed romantic relationships without marriage and cohabitation. Because of assumptions that older adults will receive family caregiving as they grow older and need caregiving, it is not clear how people are likely to perceive obligations to provide caregiving assistance. As adults move into old age and incidence rates of Alzheimer’s Disease or Related Dementia (ADRD) increase, questions about the availability of family members to provide needed assistance are complicated by LAT relationships. The purpose of this study was to examine perceived obligations to provide assistance to older adults …

Pediatric Occupational Therapists’ Perception On How Nature-Based Play Affects Fine Motor Development, Abbi M. Rosenow

Human Development and Family Sciences Undergraduate Honors Theses

This study aimed to explore the benefits of nature-based pediatric occupational therapy and the influence of nature and nature-based play on fine motor development. It was hypothesized that nature and nature-based play would positively impact a child’s fine motor skills, and that nature-based occupational therapy would offer unique benefits to a child’s therapeutic experience. To examine these relationships, a survey was distributed to pediatric occupational therapists across the United States. The survey was designed to gather insights into how occupational therapy supports fine motor development, how nature-based play/therapy enhances these skills, and the perceived benefits of incorporating nature into therapeutic …