Digital Commons Network^™

Where Did It Go Wrong? Attributing Undesirable Llm Behaviors Via Representation Gradient Tracing, Zhe Li, Wei Zhao, Yige Li, Jun Sun

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) have demonstrated remarkable capabilities, yet their deployment is frequently undermined by undesirable behaviors such as generating harmful content, factual inaccuracies, and societal biases. Diagnosing the root causes of these failures poses a critical challenge for AI safety. Existing attribution methods, particularly those based on parameter gradients, often fall short due to prohibitive noisy signals and computational complexity. In this work, we introduce a novel and efficient framework that diagnoses a range of undesirable LLM behaviors by analyzing representation and its gradients, which operates directly in the model's activation space to provide a semantically meaningful signal linking …

Propaganda Ai: An Analysis Of Semantic Divergence In Large Language Models, Nay Myat Min, Long H. Pham, Yige Li, Jun Sun

Research Collection School Of Computing and Information Systems

Large language models (LLMs) can exhibit concept-conditioned semantic divergence: common high-level cues (e.g., ideologies, public figures) elicit unusually uniform, stance-like responses that evade token-trigger audits. This behavior falls in a blind spot of current safety evaluations, yet carries major societal stakes, as such concept cues can steer content exposure at scale. We formalize this phenomenon and present RAVEN (Response Anomaly Vigilance), a black-box audit that flags cases where a model is simultaneously highly certain and atypical among peers by coupling semantic entropy over paraphrastic samples with cross-model disagreement. In a controlled LoRA fine-tuning study, we implant a concept-conditioned stance using …

Reducing Class-Wise Performance Disparity Via Margin Regularization, Beier Zhu, Kesen Zhao, Jiequan Cui, Qianru Sun, Yuan Zhou, Xun Yang, Hanwang Zhang

Research Collection School Of Computing and Information Systems

Deep neural networks often exhibit substantial disparities in class-wise accuracy, even when trained on class-balanced data—posing concerns for reliable deployment. While prior efforts have explored empirical remedies, a theoretical understanding of such performance disparities in classification remains limited. In this work, we present Margin Regularization for performance disparity Reduction (MR2 ), a theoretically principled regularization for classification by dynamically adjusting margins in both the logit and representation spaces. Our analysis establishes a margin-based, class-sensitive generalization bound that reveals how per-class feature variability contributes to error, motivating the use of larger margins for “hard” classes. Guided by this insight, MR2 optimizes …

Managing Reproducibility Debt In Scientific Software: A Practical Framework, Zara Hassan, Christoph Treude, Graham Williams, Michael Norrish, Alex Potanin

Research Collection School Of Computing and Information Systems

Scientific software includes end-user applications, modelling tools, research software for publications, and production systems for real users. It plays a key role across various scientific disciplines by enabling large-scale computation, simulation, and data analysis. Unlike commercial software, scientific software is often developed in dynamic research environments with limited engineering practices, documentation, or testing. This makes it fragile and difficult to reproduce results, even when code and data are available, conditions in which Reproducibility Debt (RpD) accumulates. This paper presents the Reproducibility Debt Management Framework (RpD-MF), which is grounded in evidence from a systematic literature review, practitioner interviews, and a global …

Real-Time Motion-Controllable Autoregressive Video Diffusion, Kesen Zhao, Jiaxin Shi, Beier Zhu, Junbao Zhou, Xiaolong Shen, Yuan Zhou, Qianru Sun, Hanwang Zhang

Research Collection School Of Computing and Information Systems

Real-time motion-controllable video generation remains challenging due to the inherent latency of bidirectional diffusion models and the lack of effective autoregressive (AR) approaches. Existing AR video diffusion models are limited to simple control signals or text-to-video generation, and often suffer from quality degradation and motion artifacts in few-step generation. To address these challenges, we propose AR-Drag, the first RL-enhanced few-step AR video diffusion model for real-time image-to-video generation with diverse motion control. We first fine-tune a base I2V model to support basic motion control, then further improve it via reinforcement learning with a trajectory-based reward model. Our design preserves the …

Llmqua: Practical Backdoor Injection On Large Language Model Quantization, Xiangxiang Chen, Peixin Zhang, Jun Sun, Jin Song Dong, Wenhai Wang, Jingyi Wang

Research Collection School Of Computing and Information Systems

Quantization is widely used to enable local deployment of large language models (LLMs) on resource-constrained devices. Recent work (e.g., QuRA) shows quantization can be exploited via rounding manipulation to implant backdoors. However, such an attack has been evaluated only on small models and does not directly apply to LLMs due to three key constraints: (1) limited poisoning data from small, task-agnostic calibration sets; (2) layer-wise quantization restricting adversarial access to global representations; and (3) lack of gradient access in quantization pipelines, blocking gradient-based attacks.We propose LLMQuA, a practical quantization-phase backdoor attack tailored to the LLM setting. LLMQuA (i) injects backdoors …

Be Responsible In Your Answers! Monitoring Out-Of-Domain Behaviors In Domain-Specific Llms, Boquan Li, Chenzhe Lou, Zhe Ren, Peixin Zhang, Zirui Fu, Jun Sun, Yaowen Zheng

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) have accelerated the rapid development of chatbot web applications in various domains, such as coding, biomedicine and psychology. Compared to general LLMs like ChatGPT, domain-specific LLMs require a greater sense of responsibility. For instance, if a programming LLM casually answers medical or psychological questions, it not only misleads the public but also poses legal risks. This highlights new demands for monitoring and preventing such irresponsible behaviors. Existing efforts attempt to monitor LLMs from multiple aspects, such as lying, jailbreaks, and toxic content, while overlooking out-of-domain behaviors. In this work, we propose an innovative LLM domain monitoring …

Prompting Frameworks For Large Language Models: A Survey, Xiaoxia Liu, Jingyi Wang, Jun Sun, Xiaohan Yuan, Guoliang Dong, Peng Di, Wenhai Wang, Dongxia Wang

Research Collection School Of Computing and Information Systems

Since the launch of ChatGPT, a powerful AI Chatbot developed by OpenAI, large language models (LLMs) have made significant advancements in both academia and industry, bringing about a fundamental engineering paradigm shift in many areas. While LLMs are powerful, it is also crucial to best use their power where “prompt” plays a core role. However, the booming LLMs themselves, including excellent APIs like ChatGPT, have several inherent limitations: (1) temporal lag of training data, and (2) the lack of physical capabilities to perform external actions. Recently, we have observed the trend of utilizing prompt-based tools to better utilize the power …

Teamwise: Exploring Virtually Embodied Ai Facilitation For Video-Based Team Onboarding, Venkata Akhila Rani Obilisetty, Mikkeline Elleby, Anthony Tang, April Yi Wang

Research Collection School Of Computing and Information Systems

AI-mediated facilitation has emerged as a scalable approach to supporting onboarding and coordination in newly formed remote teams, yet existing systems are predominantly text-based. To explore how video-based, virtually embodied AI facilitators shape team experiences, we present TeamWise, which joins video-based onboarding meetings as an on-screen avatar. TeamWise guides teams through a structured facilitation flow of low-stakes activities to foster rapport, mutual awareness, and shared identity. While the overall sequence of activities and facilitation goals is predefined, the facilitator’s turn-by-turn utterances are generated dynamically by an LLM in response to participant input. We conducted a formative study of TeamWise to …

Who You Explain To Matters: Learning By Explaining To Conversational Agents With Different Pedagogical Roles, Zhengtao Xu, Junti Zhang, Anthony Tang, Yi-Chieh Lee

Research Collection School Of Computing and Information Systems

Conversational agents are increasingly used in education for learning support. An application is “learning by explaining”, where learners explain their understanding to an agent. However, existing research focuses on single roles, leaving it unclear how different pedagogical roles influence learners’ interaction patterns, learning outcomes and experiences. We conducted a between-subjects study (N=96) comparing agents with three pedagogical roles (Tutee, Peer, Challenger) and a control condition while learning an economics concept. We found that different pedagogical roles shaped learning dynamics, including interaction patterns and experiences. Specifically, the Tutee agent elicited the most cognitive investment but led to high pressure. The Peer …

Challenges In Synchronous And Remote Collaboration Around Visualization, Matthew Brehmer, Maxime Cordeil, Christophe Hurter, Takayuki Itoh, Wolfgang Büschel, Mahmood Jasim, Arnaud Prouzeau, David Saffo, Lyn Bartram, Sheelagh Carpendale, Chen Zhu-Tian, Andrew Cunningham, Anthony Tang, Samuel Huron, Masahiko Itoh, Arpit Joshi, Kiyoshi Kiyokawa, Hideaki Kuzuoka, Bongshin Lee, Guillermo Molina León

Research Collection School Of Computing and Information Systems

We characterize 16 challenges faced by those investigating and developing remote and synchronous collaborative experiences around visualization. Our work reflects the perspectives and prior research efforts of an international group of 29 experts from across human-computer interaction and visualization sub-communities. The challenges are anchored around five collaborative activities that exhibit a centrality of visualization and multimodal communication. These activities include exploratory data analysis, creative ideation, visualization-rich presentations, joint decision making grounded in data, and real-time data monitoring. The challenges also reflect the changing dynamics of these activities in the face of recent advances in extended reality (XR) and artificial intelligence …

Reasoning On Time-Series For Financial Technical Analysis, Kelvin J. L. Koa, Jan Chen, Yunshan Ma, Huanhuan Zheng, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

While Large Language Models have been used to produce interpretable stock forecasts, they mainly focus on analyzing textual reports but not historical price data, also known as Technical Analysis. This task is challenging as it switches between domains: the stock price inputs and outputs lie in the time-series domain, while the reasoning step should be in natural language. In this work, we introduce Verbal Technical Analysis (VTA), a novel framework that combine verbal and latent reasoning to produce stock time-series forecasts that are both accurate and interpretable. To reason over time-series, we convert stock price data into textual annotations and …

Visual Loop: Bridging The Cognitive Gap In Software Development Through Visual-Ai Collaboration, Luis Filipe Fernandes Gomes, Xin Zhou, David Lo, Rui Abreu

Research Collection School Of Computing and Information Systems

Software development remains predominantly text-centric, despite decades of evidence showing that developers think and communicate visually. While sketches and diagrams externalize developers’ mental models, they remain disconnected from source code and quickly become outdated. Recent advances in foundation models, capable of both code and visual reasoning, create an opportunity to unify these representations. In this vision paper, we introduce Visual Loop, a continuous visual development environment that keeps code and informal sketches in bidirectional synchronization. Our prototype connects a code editor with a tablet-based visualization workspace, allowing developers to explore, annotate, and modify systems through freehand sketches interpreted by multimodal …

Understanding Codebase Like A Professional! Human-Ai Collaboration For Code Comprehension, Jie Gao, Yue Xue, Xiaofei Xie, Junming Cao, Soemin Thant, Erika Lee, Bowen Xu

Research Collection School Of Computing and Information Systems

Understanding an unfamiliar codebase is an essential task for developers in various scenarios, such as during the onboarding process. Especially when the codebase is large and time is limited, achieving a decent level of comprehension remains challenging for both experienced and novice developers, even with the assistance of large language models (LLMs). Existing studies have shown that LLMs often fail to support users in understanding code structures or to provide user-centered, adaptive, and dynamic assistance in real-world settings.To address this, we propose learning from the perspective of a unique role, code auditors, whose work often requires them to quickly familiarize …

Autobackdoor: Automating Backdoor Attacks Via Llm Agents, Yige Li, Zhe Li, Wei Zhao, Nay Myat Min, Hanxun Huang, Xingjun Ma, Jun Sun

Research Collection School Of Computing and Information Systems

Backdoor attacks pose a serious threat to the secure deployment of large language models (LLMs), enabling adversaries to implant hidden behaviors triggered by specific inputs. However, existing methods often rely on manually crafted triggers and static data pipelines, which are rigid, labor-intensive, and inadequate for systematically evaluating modern defense robustness. As AI agents become increasingly capable, there is a growing need for more rigorous, diverse, and scalable \textit{red-teaming frameworks} that can realistically simulate backdoor threats and assess model resilience under adversarial conditions. In this work, we introduce \textsc{AutoBackdoor}, a general framework for automating backdoor injection, encompassing trigger generation, poisoned data …

Approaches And Barriers To Cultivating Critical Thinking Skills For Effective Clinical Decision Making, Yousif Abdulraheem

Iraqi Postgraduate Medical Journal

Clinical decision-making is a complex process that involves gathering information, analyzing data, making informed judgments, and taking appropriate actions for a patient's care. Critical thinking (CT) is a vital component of this process, as it enables healthcare professionals to evaluate information, identify biases and assumptions, and make informed decisions (1). It requires careful consideration of multiple factors, including the patient's age, gender, medical history, physical exams, and diagnostic test results, health status, lifestyle, and even preferences, to develop a diagnosis and treatment plan. In recent years, there has been a growing recognition of the importance of promoting CT skills in …

Exploring The Physical Education Experiences Of Blind And Visually Impaired Hispanic Multilingual Learners In Integrated Settings, Sheyla G. Martinez-Rivera

Human Movement Studies & Special Education Theses & Dissertations

Although students with visual impairments (VI) are increasingly placed in integrated physical education (PE) classes (U.S. Department of Education, 2023), the embodied experiences of those who also identify as multilingual learners (MLs) and as Hispanics remain largely unexplored. This retrospective qualitative study examined how these students experience integrated PE during their K-12 education, focusing on how language and disability identities shaped their participation. Participants included seven Hispanic students, all MLs, and identified under the Individuals with Disabilities Education Act (IDEA) as blind or visually impaired. At the time of the study, participants were between 18 and 33 years old and …

Exploring The Perceptions Of United States Dentists And Dental Hygienists Towards Implementation Of New Workforce Shortage Policies, Hite N. Jones

Dental Hygiene Theses & Dissertations

Background: There is a perceived national dental hygiene shortage causing delays in receiving preventive treatment and potentially increasing oral disease risk. States are proposing alternative pathways to allow less-trained individuals to provide dental hygiene care to fill this perceived gap. There is no research to support whether such measures would mitigate the shortage issue. Purpose: Therefore, the purpose of this study was to examine the perceptions of United States (U.S.) dentists and dental hygienists (DH) towards the implementation of new workforce shortage policies and contributing factors and solutions to the workforce shortage. Methods: This descriptive, cross-sectional study included a convenience …

Assessing Stakeholders’ Perceptions Of Organizational Effectiveness Through A Multidimensional Theoretical Model: An Interpretive Phenomenological Qualitative Case Study, Andrea M. Paul

School of Public Service Theses & Dissertations

Nonprofit organizations play a fundamental role in meeting community needs when government resources are limited or nonexistent. For decades, scholars and practitioners have recognized the importance of nonprofit-government partnerships for effective public service delivery. This study examines faith-based organizations as a specific type of hybrid nonprofit organization. As social, economic, and environmental challenges intensify, the need for community-based programs led by faith-based organizations also increases. These organizations are working to combat several of society's wicked problems, including but not limited to homelessness, food insecurity, drug addiction, youth and family services, and climate change. Nonprofit sector performance measurement is often recognized …

Cavitation-Aware Design Of Hydrofoil Sections For Marine Propeller Blade Development, Samuel G. Bacon

Mechanical & Aerospace Engineering Theses & Dissertations

Cavitation is a major design constraint for marine propeller blade sections because it can reduce hydrodynamic performance, increase vibration and noise, and contribute to surface damage. This thesis develops and applies an exploratory computational framework for cavitation-aware hydrofoil-section design relevant to marine propeller blade development. The framework combines section-level CFD validation, CST-based geometry parameterization, pressure-based pre-screening, matched-load comparison, and focused predicted inception envelope or cavitation-bucket analysis.

The CFD methodology was validated against published YS-920 hydrofoil water-tunnel data using selected fully wetted, near-inception, and cavitating reference cases. The validation results showed that the adopted framework reproduced the key experimental trends needed …

Empowering Change: Building Environmental Sustainability Initiatives And Becoming A Sustainability Champion, Amanda C. Karls

School of Public Service Theses & Dissertations

In an era marked by escalating environmental challenges and an urgent need for sustainable development, higher education institutions (HEIs) are increasingly positioned as critical actors in advancing sustainability within the communities they serve. Regional comprehensive universities (RCUs), in particular, occupy a distinctive position as access‑oriented, community‑embedded public institutions; yet sustainability efforts at these institutions often unfold under conditions of limited resources, diffuse responsibility, and informal governance. This dissertation examines how individual actors at RCUs effectively advance environmental sustainability initiatives in the absence of centralized infrastructure or formal authority.

Guided by the overarching research question—How can individual actors at regional comprehensive …

Perceptions Of Virginia Dentists And Dental Hygienists Towards Emerging Alternative Dental Hygiene Workforce Provider Models, Lauren B. Mangum

Dental Hygiene Theses & Dissertations

Background: A perceived shortage of dental hygienists in the United States has been linked to delays in preventive care and concerns about declining oral health outcomes. In response, some states have proposed alternative pathways permitting internationally trained dentists, dental students, and oral preventive assistants (OPAs) with limited or inconsistent education requirements to provide dental hygiene services. Limited evidence exists regarding whether these strategies would effectively address access to care and workforce challenges. Concerns have also been raised about the potential effects of expanding scope of practice for providers with limited education or training on patient safety and quality of care. …

Ultra-High Vacuum Outgassing Characterization Of Thermally Processed Low-Carbon Steel For Advanced Particle Accelerator And Gravitational Wave Detector Applications, Aiman H. Al-Allaq

Mechanical & Aerospace Engineering Theses & Dissertations

This dissertation investigated AISI 1020 low-carbon steel as an alternative vacuum chamber material to conventional stainless steel for ultra-high vacuum (UHV) and extreme-high vacuum (XHV) applications. After a 400 °C/48 h bake, AISI 1020 tube chambers achieved a hydrogen outgassing rate of 2.4 × 10⁻¹⁶ Torr·L·s⁻¹·cm⁻², approximately 2,300 times lower than the prebaked 316L stainless-steel comparator, among the lowest hydrogen outgassing rates ever reported for an uncoated metallic vacuum chamber. Bare and magnetite-coated AISI 1020 chambers were then compared using throughput and rate-of-rise methods. The magnetite coating yielded 5× lower water outgassing at room temperature, but this advantage disappeared after …

Dissecting The Etiology Of Alcohol Use Disorder By An Integrative Heritable Component Approach, Ivy Garrenton

Computer Science Theses & Dissertations

Alcohol Use Disorder (AUD) is a pervasive condition characterized by complex interplay among genetic, phenotypic, and environmental factors. Although previous studies have identi fied genetic loci associated with alcohol consumption, these efforts have not captured the genetic heterogeneity and gene-environment interactions underlying AUD pathogenesis. To address this critical gap, we developed a novel statistical methodology that integrates phenotypic, genotypic, and environmental data through an environmentally modified Genetic Relationship Matrix (GRM) to derive AUD-related traits with enhanced heritability.

This approach demonstrated superior performance in both simulated and real-world datasets. Traits derived using the environmentally modified GRM exhibited significantly higher estimated heritability …

Artificial Intelligence For Better Inclusive Higher Education: A Study Of A Private University In Cairo, Shereen Ismail

Theses and Dissertations

This study explores how artificial intelligence (AI) tools relate to accessibility for visually impaired students in Egyptian higher education, focusing on University Y in Cairo. Grounded in the Social Model of Disability and Universal Design for Learning, it examines visually impaired students’ lived experiences of AI mediated access and the institutional conditions that shape these experiences. A qualitative phenomenological design was used, with semi-structured interviews conducted with visually impaired undergraduate students and key staff involved in assistive technology, teaching and learning, and student wellbeing; data were analyzed thematically. The findings indicate that participants experience AI tools (e.g., chatbots, transcription and …

Library 5.0 And Predictive Intelligence: A Conceptual Literature Review, Shrikant Ramteke

Library Philosophy and Practice (e-journal)

Abstract

Purpose In this paper, the author will explore the nature of predictive intelligence developed in modern libraries as part of the overall progression of libraries toward Library 5.0. It aims to give a conceptual clarity of what predictive services are, how they have been influenced by technology and ethics, and how they fit into existing traditions of librarianship.

Design/methodology/approach This paper utilizes a qualitative, conceptual literature review method as a scholarly inquiry. Approximately 60 peer-reviewed journal articles and institutional reports published after 2018 and before 2025 were purposively sampled from leading databases in library and information science and information …

Geography And Environmental Studies Apr 2025 Self-Study Report & Documents, Unm Academic Program Review

UNM Academic Program Review

NM Geography and Environmental Studies APR self-study report, review team report, response report, and initial action plan for AY2025, fulfilling requirements of the Higher Learning Commission.

Rural Transformations And Identity In Northern New Mexico, Eva Gemrich

Geography ETDs

In the U.S. West, research points to a significant transformation of rural places, including rural blight, a decline in extractive industries, and changing migration patterns. In Northern New Mexico, these rural transformations are occurring alongside a long and continuing history of tensions and conflicts relating to land, water, and property regimes, which are intertwined with notions of identity, culture, and power. Using participant observation and semi-structured interviews, this thesis explores how rural transformations, particularly shifting land ownership, have influenced identities and cultural values along the Upper Rio Chama in Northern New Mexico. I find that comparatively wealthy in-migrants are purchasing …

Transcending Shelves And Seashells With The Writing Of Gloria E. Anzaldúa, Dr. Inmaculada Lara-Bonilla

LAII Events

Dr. Lara-Bonilla explores how Gloria E. Anzaldúa understood writing as an embodied, transformative practice that dissolves boundaries between the physical, the intellectual, and the spiritual. Drawing on her archival and posthumous work, it reflects on how her experimental, genre-crossing approach challenges academic conventions and invites new ways of thinking, feeling, and writing. Tracing a long-term engagement with her work, the talk narrates how Anzaldúa’s commitment to preserving lived, “poematic” experience has reshaped Dr. Lara Bonilla’s own scholarly and creative practice, pushing it beyond institutional limits toward more expansive and responsive forms of expression.

Development And Acceptability Of A Patient Decision Aid For People With Degenerative Cervical Myelopathy: An International Mixed-Methods Study, Andrew R. Gamble, David B. Anderson, Marnee J. Mckay, Benjamin M. Davies, Sophie Macpherson, James Van Gelder, Tammy Hoffmann, Kirsten Mccaffery, Samuel X. Stevens, Carlo Ammendolia, Rohil V. Chauhan, Carl M. Zipser, Timothy F. Boerger, Lindsay A. Tetreault, Michael G. Fehlings, Elanor Dustan, Carolyn Nugent, Helen Holmgren, Andreas K. Demetriades, Justin M. Lantz, Rana Dhillon, Chris G. Maher, Joshua R. Zadro

Biomedical Engineering Faculty Research and Publications

Objectives To develop and user-test a patient decision aid for people diagnosed with degenerative cervical myelopathy and who are considering surgery.

Design Mixed-methods study describing the development of a patient decision aid.

Setting A draft decision aid was developed by a multidisciplinary steering group (including study authors with degenerative cervical myelopathy, health professionals and researchers) informed by the best available evidence, authorship consensus and existing patient decision aids.

Participants Patient-participants and health professional-participants who manage people with degenerative cervical myelopathy were recruited through social media and the steering group’s research and practice network. Quantitative questionnaires were used to gather baseline …