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 …

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) …

Enhancing Non-Visual Interaction With Online User-Generated Content, Mohan Krishna Sunkara

Computer Science Theses & Dissertations

The Web has become the dominant medium for our everyday activities, including communication, business, e-commerce, news, and entertainment. Consequently, the online world is experiencing an explosion of User-Generated Content (UGC), particularly on social media platforms and online review systems. To facilitate convenient interaction with UGC, web platforms have adopted various presentation strategies that enable users to efficiently browse and contribute to the UGC. However, these user interfaces are primarily designed for sighted individuals, so they do little to assist blind users who rely predominantly on audio-based screen reader assistive technology. The extant efforts to improve web interaction for blind users …

Sccosmix: A Mixed-Effects Framework For Differential Coexpression And Transcriptional Interactions Modeling In Single-Cell Rna-Seq, Anderson Bussing, Giampiero Marra, Daping Fan, Russell Shinohara, Danni Tu, Yen-Yi Ho

Faculty Publications

Advancements in single-cell RNA-sequencing (scRNA-seq) technologies generate a wealth of gene expression data that provide exciting opportunities for studying gene-gene interactions systematically at individual cell resolution. Genetic interactions within a cell are tightly regulated and often highly dynamic in response to internal cellular signals and external stimuli. Evidence of these dynamic interactions can often be observed in scRNA-seq data by examining conditional co-expression changes. Existing approaches for studying these dynamic interaction changes in scRNA-seq data do not address the multi-subject hierarchical design commonly considered in single-cell experiments. In this paper, we propose a Mixed-effects framework for differential Coexpression and transcriptional …

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 …

Do Themes Improve Visitor Outcomes In Interpretive Programs?, Amber K. Hawes

All Theses

Thematic interpretation is widely promoted as being integral to an effective interpretive program. Some studies have suggested that thematic interpretation may enhance visitor outcomes; however, park visitor demographics have changed over the last decade, and others have suggested alternative approaches. In this study, we systematically observed live interpretive programs at 330 programs at 52 National Parks across the United States, monitored the extent and characteristics of theme usage, and collected visitor surveys immediately following each program. We used these data to determine the influence of the presence and characteristics of themes and theme questions on visitor outcomes. The results suggest …

Enhancing The Value Of Satellite Earth Observations For Coastal Management: Tools For Collaboration And Co-Development, Nicole Dejeet Bartlett

Graduate Doctoral Dissertations

Despite unprecedented satellite Earth observation (EO) capabilities and free data availability, widespread adoption in coastal management remains limited due to persistent communication barriers between satellite experts and coastal practitioners. This dissertation addresses the fundamental challenge of translating satellite EO technical capabilities into management-relevant applications. Through synthesis of literature, stakeholder interviews, and two multi-year co-development case studies in Virginia's Middle Peninsula and Cape Cod, Massachusetts, this research identifies systematic barriers to satellite EO adoption and develops innovative frameworks for overcoming them.

The work argues for a common language between satellite product developers and coastal managers, identifying communication barriers spanning technical, institutional, …

Rhetorics Of Encounter: Toward A Biocentric Theory Of Discourse, Matthew D. Whitaker

Dissertations and Doctoral Documents, University of Nebraska-Lincoln, 2023–

Encounters with more-than-human identities are transformative moments that stand to affect dispositional and bodily change in individuals. From close brushes with wild animals in National Parks to everyday interactions with local ecologies, encounters invite us to feel and think differently about the nature of our realities. In Rhetorics of Encounter: Toward a Biocentric Theory of Discourse, I draw from interdisciplinary perspectives to disrupt the idea of rhetoric as a representational medium, arguing that rhetoric occurs not just through textual exchanges of words and symbols, but through embodied moments of contact with other responsive beings. Invoking George Kennedy’s theory …

Development And Evaluation Of Supported Ionic Liquid Membrane And Porphyrin Frameworks For Carbon Capture Separation, Sarang Ismail

Dissertations and Doctoral Documents, University of Nebraska-Lincoln, 2023–

The global urgency to mitigate anthropogenic CO₂ emissions has intensified the pursuit of energy-efficient separation technologies. Supported Ionic Liquid Membranes (SILMs) have emerged as promising candidates for CO₂ capture due to their tunable solubility-selectivity and low energy requirements. However, challenges such as mechanical instability, limited scalability, and trade-offs in transport performance have impeded their widespread adoption.

This thesis explores a systematic approach to designing and optimizing SILMs for enhanced CO₂ separation by tailoring polymer–ionic liquid interactions, processing conditions, and material architectures. A comprehensive set of studies were conducted using poly(vinylidene fluoride) (PVDF) with varying molecular weights, different grades of PEBAX®, …

Service With A Smile Or Salesperson Mirroring? Understanding The Flow Of Emotional Contagion In Sales Encounters, Vinh Quoc Trong Luong

Theses and Dissertations in Business Administration

This study examines the directionality of emotional contagion in sales interactions, addressing a critical gap in understanding whether emotions flow primarily from the salesperson to the customer, from the customer to the salesperson, or bidirectionally. While prior research emphasizes customer-driven emotional flow or bidirectional alignment, this study challenges these assumptions by employing categorical Cross-Recurrence Quantification Analysis (CRQA) to assess temporal emotional synchronization in sales dialogues. Leveraging automated sentiment analysis and multi-agent AI evaluation for performance metrics, the research analyzes 166 sales interactions to quantify emotional influence dynamics. Results reveal that salespeople predominantly lead emotional exchanges, exhibiting stronger and more stable …

Mantle Flow And Crustal Deformation Revealed By Seismic Anisotropy In The Subduction Zone Beneath Myanmar, Enbo Fan, Mingming Jiang, Yinshuang Ai, Stephen S. Gao, Kelly H. Liu, Yumei He, Yiming Bai, Guangbing Hou, Yuan Ling, Chit Thet Mon, Myo Thant, Kyaing Sein

Geosciences and Geological and Petroleum Engineering Faculty Research & Creative Works

The oblique convergence of the Indian and Eurasian plates drives significant deformation in the crust and mantle beneath Myanmar. However, the crustal deformation in the Indo-Burman Ranges (IBR) and mantle flow beneath Myanmar and adjacent areas remain unclear due to limited studies. We utilized data from the newly deployed second phase of the China-Myanmar Geophysical Survey of the Myanmar Orogen array to perform shear wave splitting analysis of PKS, SKKS, and SKS (XKS) phases. Our results, together with previous findings, provide new insights into mantle flow and crustal deformation across central Myanmar. In the IBR, we observed a transition from …

Explainable Machine Learning Surrogate Modeling For Exit Gradient Prediction In Hydraulic Structures Using Numerical Simulations, Prayas Rath, Jianting Zhu, Kevin M. Befus

Geosciences Faculty Publications and Presentations

Accurate prediction of exit gradients is essential for designing impounding hydraulic structures, such as dams and levees, to mitigate seepage-induced piping failures. Conventional analytical methods often neglect boundary effects and anisotropy, limiting their applicability in complex geological settings. This study develops an XGBoost-based machine learning surrogate model trained and tested on 8,000 MODFLOW numerical simulations to predict exit gradients under varying hydraulic and geological conditions. The data set covers numerous parameters, including anisotropy, head differences, structure width, cut-off wall depth, aquifer thickness, and uninterrupted riverbed length. The coefficient of determination for test data is 0.88, demonstrating reliable exit gradient prediction …

A Multi-Source Remote Sensing-Based Geocommunication Tool For Global Flood Monitoring And Management, Ebrahim Hamidi, Brad Peter, Hamed Moftakhari, Hamid Moradkhani

Geosciences Faculty Publications and Presentations

Global warming is expected to increase the frequency of extreme flooding, making rapid and accurate flood mapping crucial for effective risk assessment. Many governmental agencies and organizations are developing flood risk assessment tools; however, due to the lack of observational records, some rely on probabilistic generated data, uncalibrated simulations, or terrain-based methods, all of which are subject to various types of uncertainty. Although remote sensing provides valuable flood data with global coverage, single-source reliance is constrained by satellite revisit rates, resolution, weather conditions, and sensor limitations. To address these challenges, this study introduces a user-friendly application on the Google Earth …