Digital Commons Network^™

Instructors’ Strategies In Creating And Implementing Constructivist Llm-Based Learning Activities, Emily Aurelia, Shun Yi Yeo, Michelle Lui, Effie Lai-Chong Law, Anthony Tang

Research Collection School Of Computing and Information Systems

Large language models (LLMs) are increasingly being integrated into educational settings, enabling more adoption of constructivist teaching and learning approaches in classrooms. This paper explores the strategies instructors are currently using to incorporate LLMs into learning activities that align with constructivist principles, which emphasize that learners actively construct their own knowledge. Through interviews with nine instructors who have designed eleven distinct LLM-based activities and using reflexive thematic analysis, this study identifies various types of learning activities with respect to four different aspects of the constructivist learning theory. The strategies employed and challenges faced to foster constructivist student-LLM interaction were also …

Seeing Culture: A Benchmark For Visual Reasoning And Grounding, Burak Satar, Zhixin Ma, Patrick Amadeus Irrawan, Wilfried Ariel Mulyawan, Jing Jiang, Ee-Peng Lim, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

Multimodal vision-language models (VLMs) have made substantial progress in various tasks that require a combined understanding of visual and textual content, particularly in cultural understanding tasks, with the emergence of new cultural datasets. However, these datasets frequently fall short of providing cultural reasoning while underrepresenting many cultures.In this paper, we introduce the Seeing Culture Benchmark (SCB), focusing on cultural reasoning with a novel approach that requires VLMs to reason on culturally rich images in two stages: i) selecting the correct visual option with multiple-choice visual question answering (VQA), and ii) segmenting the relevant cultural artifact as evidence of reasoning. Visual …

Seeing Is Fixing: Cross-Modal Reasoning With Multimodal Llms For Visual Software Issue Fixing, Kai Huang, Jian Zhang, Xiaofei Xie, Chunyang Chen

Research Collection School Of Computing and Information Systems

Large language model (LLM)-based automated program repair (APR) techniques have shown promising results in resolving real-world github issue tasks. Existing APR systems are primarily evaluated in unimodal settings (e.g., SWE-bench), relying solely on textual issue descriptions and source code. However, these autonomous systems struggle to resolve multimodal problem scenarios (e.g., SWE-bench M) due to limitations in interpreting and leveraging visual information. In multimodal scenarios, LLMs need to rely on visual information in the graphical user interface (GUI) to understand bugs and generate fixes. To bridge this gap, we propose GUIRepair, a cross-modal reasoning approach for resolving multimodal issue scenarios by …

Mmlu-Prox: A Multilingual Benchmark For Advanced Large Language Model Evaluation, Weihao Xuan, Et. Al.

Research Collection School Of Computing and Information Systems

Existing large language model (LLM) evaluation benchmarks primarily focus on English, while current multilingual tasks lack parallel questions that specifically assess cross-lingual reasoning abilities. This dual limitation makes it challenging to assess LLMs’ performance in the multilingual setting comprehensively. To fill this gap, we introduce MMLU-ProX, a comprehensive benchmark covering 29 languages, built on an English benchmark. Each language version consists of 11,829 identical questions, enabling direct cross-lingual comparisons. Additionally, to meet efficient evaluation needs, we provide a lite version containing 658 questions per language. To ensure the high quality of MMLU-ProX, we employ a rigorous development process that involves …

From Personas To Talks: Revisiting The Impact Of Personas On Llm-Synthesized Emotional Support Conversations, Shenghan Wu, Yimo Zhu, Wynne Hsu, Mong-Li Lee, Yang Deng

Research Collection School Of Computing and Information Systems

The rapid advancement of Large Language Models (LLMs) has revolutionized the generation of emotional support conversations (ESC), offering scalable solutions with reduced costs and enhanced data privacy. This paper explores the role of personas in the creation of ESC by LLMs. Our research utilizes established psychological frameworks to measure and infuse persona traits into LLMs, which then generate dialogues in the emotional support scenario. We conduct extensive evaluations to understand the stability of persona traits in dialogues, examining shifts in traits post-generation and their impact on dialogue quality and strategy distribution. Experimental results reveal several notable findings: 1) LLMs can …

Adasteer: Your Aligned Llm Is Inherently An Adaptive Jailbreak Defender, Weixiang Zhao, Jiahe Guo, Yulin Hu, Yang Deng, An Zhang, Xingyu Sui, Xinyang Han, Yanyan Zhao, Bing Qin, Tat-Seng Chua, Ting Liu

Research Collection School Of Computing and Information Systems

Despite extensive efforts in safety alignment, large language models (LLMs) remain vulnerable to jailbreak attacks. Activation steering offers a training-free defense method but relies on fixed steering coefficients, resulting in suboptimal protection and increased false rejections of benign inputs. To address this, we propose AdaSteer, an adaptive activation steering method that dynamically adjusts model behavior based on input characteristics. We identify two key properties: Rejection Law (R-Law), which shows that stronger steering is needed for jailbreak inputs opposing the rejection direction, and Harmfulness Law (H-Law), which differentiates adversarial and benign inputs. AdaSteer steers input representations along both the Rejection Direction …

Exploring Autonomous Agents: A Closer Look At Why They Fail When Completing Tasks, Ruofan Lu, Yichen Li, Yintong Huo

Research Collection School Of Computing and Information Systems

Autonomous agent systems powered by Large Language Models (LLMs) have demonstrated promising capabilities in automating complex tasks. However, current evaluations largely rely on success rates without systematically analyzing the interactions, communication mechanisms, and failure causes within these systems. To bridge this gap, we present a benchmark of 34 representative programmable tasks designed to rigorously assess autonomous agents. Using this benchmark, we evaluate three popular open-source agent frameworks combined with two LLM backbones, observing a task completion rate of approximately 50%. Through in-depth failure analysis, we develop a three-tier taxonomy of failure causes aligned with task phases, highlighting planning errors, task …

Envisioning Future Interactive Web Development: Editing Webpage With Natural Language, Truong Hai Dang, Jingyu Xiao, Yintong Huo

Research Collection School Of Computing and Information Systems

The evolution of web applications relies on iterative code modifications, a process that is traditionally manual and time-consuming. While Large Language Models (LLMs) can generate UI code, their ability to edit existing code from new design requirements (e.g., ”center the logo”) remains a challenge. This is largely due to the absence of large-scale, high-quality tuning data to align model performance with human expectations. In this paper, we introduce a novel, automated data generation pipeline that uses LLMs to synthesize a high-quality fine-tuning dataset for web editing, named Instruct4Edit. Our approach generates diverse instructions, applies the corresponding code modifications, and performs …

Interaction2code: Benchmarking Mllm-Based Interactive Webpage Code Generation From Interactive Prototyping, Jingyu Xiao, Yuxuan Wan, Yintong Huo, Zixin Wang, Xinyi Xu, Wenxuan Wang, Zhiyao Xu, Yuhang Wang, Michael R. Lyu

Research Collection School Of Computing and Information Systems

Multimodal Large Language Models (MLLMs) have demonstrated remarkable performance on the design-to-code task, i.e., generating UI code from UI mock-ups. However, existing benchmarks only contain static web pages for evaluation and ignore the dynamic interaction, limiting the practicality, usability and user engagement of the generated webpages. To bridge these gaps, we present the first systematic investigation of MLLMs in generating interactive webpages. Specifically, we formulate the Interaction-to-Code task and establish the Interaction2Code benchmark, encompassing 127 unique webpages and 374 distinct interactions across 15 webpage types and 31 interaction categories. Through comprehensive experiments utilizing state-of-theart (SOTA) MLLMs, evaluated via both automatic …

Intentionframe: A Semi-Structured, Multi-Aspect Framework For Fine-Grained Conversational Intention Understanding, Zailong Tian, Zhuoheng Han, Lizi Liao, Lizi Liao

Research Collection School Of Computing and Information Systems

Understanding user intentions in multi-turn dialogues is critical for conversational AI, yet existing approaches—relying on rigid slot-value structures or unstructured free-text—fail to fully capture conversational complexity. In this paper, we propose IntentionFrame, a semi-structured framework inspired by psychological and cognitive intention theories, which organizes conversational intents into four interrelated aspects: situation, emotion, action, and knowledge. This design not only retains interpretability but also provides LLMs with a rich context to accurately parse and respond to nuanced user inputs. To efficiently scale IntentionFrame annotations, we introduce a Weakly-supervised Reinforced Generation (WeRG) method that leverages a small set of high-quality human annotations …

One Planner To Guide Them All! Learning Adaptive Conversational Planners For Goal-Oriented Dialogues, Huy Dao, Lizi Liao

Research Collection School Of Computing and Information Systems

Goal-oriented dialogues, such as recommendation and negotiation, often require balancing multiple, conflicting objectives. Existing methods typically involve training separate models for specific combinations of objectives, leading to computational and scalability issues. In this work, we aim to develop a new dialogue policy method that can adapt to varying objective preferences at inference time without retraining. This raises several challenges in terms of both (1) optimization strategy and (2) knowledge utilization. To address these, we propose a novel learning framework, Preference Adaptive Dialogue Policy Planner (PADPP), for multi-objective goal-oriented dialogues. Specifically, to tackle the former, we introduce a novel policy optimization …

Context-Aware Hierarchical Taxonomy Generation For Scientific Papers Via Llm-Guided Multi-Aspect Clustering, Kun Zhu, Lizi Liao, Yuxuan Gu, Lei Huang, Xiaocheng Feng, Bing Qin

Research Collection School Of Computing and Information Systems

The rapid growth of scientific literature demands efficient methods to organize and synthesize research findings. Existing taxonomy construction methods, leveraging unsupervised clustering or direct prompting of large language models (LLMs), often lack coherence and granularity. We propose a novel context-aware hierarchical taxonomy generation framework that integrates LLM-guided multi-aspect encoding with dynamic clustering. Our method leverages LLMs to identify key aspects of each paper (e.g., methodology, dataset, evaluation) and generates aspect-specific paper summaries, which are then encoded and clustered along each aspect to form a coherent hierarchy. In addition, we introduce a new evaluation benchmark of 156 expert-crafted taxonomies encompassing 11.6k …

Why Stop At One Error? Benchmarking Llms As Data Science Code Debuggers For Multi-Hop And Multi-Bug Errors, Zhiyu Yang, Shuo Wang, Yukun Yan, Yang Deng

Research Collection School Of Computing and Information Systems

LLMs are transforming software development, yet current code generation and code repair benchmarks mainly assess syntactic and functional correctness in simple, single-error cases. LLMs’ capabilities to autonomously find and fix runtime logical errors in complex data science code remain largely unexplored. To address this gap, we introduce DSDBench: the Data Science Debugging Benchmark, the first benchmark for systematic evaluation of LLMs on multi-hop error tracing and multi-bug detection in data science code debugging. DSDBench adapts datasets from existing data science task benchmarks, such as DABench and MatPlotBench, featuring realistic data science debugging tasks with automatically synthesized multi-hop, multi-bug code snippets. …

The Ai-Powered Learning Loop In Higher Education, Oualid Abidi, Vladimir Dzenopoljac, Aleksandra Dzenopoljac

All Works

Purpose – This study examines how generative AI tools affect business students’ academic performance by investigating whether flexible AI policies promote deeper learning, enhance self-efficacy and facilitate tacit knowledge acquisition in a Middle Eastern context, while ensuring efficiency and academic integrity. Design/methodology/approach – A qualitative, exploratory study observed 20 final-year business students in Kuwait during five in-class activities using generative AI tools. Semi-structured interviews complemented the researcher’s observations. Thematic analysis revealed patterns in benefits, challenges and learning processes, leading to the development of the AI-powered learning loop framework to explain academic performance outcomes. Findings – The study indicates that generative …

Enhanced Privacy Preserving Healthcare Data Management With Federated Learning Using Homomorphic Encryption, Omar Abdulla Ali

Theses

Federated Learning (FL) is a decentralized approach of machine learning on multiple clients jointly training models without sharing their raw data, which drastically improves privacy and enhance protection against security breach. This is particularly critical in the healthcare sector, where hospitals and medical institutions are often unable to exchange patient records due to strict privacy regulations and data-management policies. However, there is still a risk of privacy breach when clients send their model updates to the central server, because if a model update is intercepted or analyzed by a malicious entity, it could be used to recover sensitive data using …

Watersmart Farms - Desalination: Best Practice Study On Desalination In Agriculture, V Ravisankar, W Ela, M Maharjan, J K. Ruprecht

Natural resources commissioned reports

Freshwater scarcity is a pressing global issue that affects people and all living organisms in different contexts, and agriculture is one of the most affected sectors. The issue is becoming more significant with unprecedented continental drying and shrinking freshwater availability (Chandanpurkar, et al., 2025). Globally this reduction in freshwater sources poses a significant challenge to not only maintaining a regular supply for a growing population but also for agriculture, both dryland and irrigated.

Synthesis And Evaluation Of Bodipy-, Azabodipy- And Chlorin-Based Conjugates For Imaging And Photodynamic Therapy Of Egfr-Overexpressing Cancers, Simran Dhingra

LSU Doctoral Dissertations

This dissertation discusses the design of EGFR-targeted small-molecule agents that unite molecular imaging with photodynamic therapy. Chapter 1 frames the clinical need for early detection and selective treatment and surveys BODIPY, aza-BODIPY, and chlorin scaffolds as tunable chromophores for near-infrared imaging and photosensitization. It also outlines EGFR as a validated target and compares two ligand classes used throughout this work: the tyrosine kinase inhibitor erlotinib and the cyclic peptide KLARLLT.

Chapter 2 describes the synthesis of a near-IR BODIPY bearing either one or two erlotinib units. Docking and SPR show specific interactions with the EGFR kinase domain, and both conjugates …

Ecophysiological Benefits Of Industrial Organic Wastes On Alfalfa Yield And Stress Mitigation In Saline Soils, Shugao Fan, Zhuanzhuan Ma, Jiawei Wu, Tianhui Yang, Jincheng Hao, Shumei Chen, Xutong Hu, Ying Zhao

School of Mathematical & Statistical Sciences Faculty Publications

Rising soil salinity and water scarcity demand sustainable solutions to maintain crop productivity. This study evaluated four agro-industrial organic amendments—fish emulsion, neem cake, coffee grounds, and seaweed extract on alfalfa (Medicago sativa) under combined salinity and drought stress, assessing their effects on soil respiration, plant physiology, and yield. Soil CO₂ efflux varied significantly among treatments: coffee grounds induced the highest microbial activity (6.2 μmol m⁻² s⁻¹), suggesting rapid decomposition, while neem cake exhibited stable emissions (3.8 μmol m⁻² s⁻¹), indicating slower organic matter turnover. Fish emulsion showed intermediate dynamics, peaking at 4.8 μmol m⁻² s⁻¹ by week 4, …

Paclobutrazol Enhances Tall Fescue Salt Tolerance Via Physiological And Root System Architecture Modulation, Shugao Fan, Xindi Sun, Guohao Liang, Zhuanzhuan Ma, Jincheng Hao, Jiawei Wu, Ying Zhao

School of Mathematical & Statistical Sciences Faculty Publications

Background: Salinity represents a major global constraint on crop productivity. Promoting the cultivation of tall fescue in saline environments offers not only nutritional advantages for livestock but also enhances its potential for ornamental use. In this mesocosm study, we examined the effects of paclobutrazol (PBZ) on tall fescue performance under salt stress, focusing on key physiological traits to evaluate salt tolerance.

Results: Under high salt stress, paclobutrazol application increased the total number of lateral roots by 85%, from 18.39 to 34.04, and widened their growth angle by 24%, from 24.10° to 29.88°, fundamentally enhancing topsoil exploration. This reconfigured root system …

Pfaffian Solution For Dark–Dark Soliton To The Coupled Complex Modified Korteweg–De Vries Equation, Chenxi Li, Xiaochuan Liu, Bao-Feng Feng

School of Mathematical & Statistical Sciences Faculty Publications

In this paper, we study the coupled complex modified Korteweg–de Vries (ccmKdV) equation by combining the Hirota’s method and the Kadomtsev–Petviashvili (KP) reduction method. First, we show that the bilinear form of the ccmKdV equation under nonzero boundary condition is linked to the discrete BKP hierarchy through Miwa transformation. Based on this finding, we construct the dark–dark soliton solution in the pfaffian form. The dynamical behaviors for one- and two-soliton are analyzed and illustrated.

Universal Crackling Noise Links Plasticity In Nanoindentation With Compression In Metallic Glasses, Jordan Sickle, Wesley H. Higgins, Kerry A. Baker, Mayisha Nakib, Xiaojun Gu, George M. Pharr, Wendelin Wright, Karin A. Dahmen

Faculty Journal Articles

For decades, compression tests have been a standard method for identifying materials properties. However, these tests are slow, destructive, and require fabricating multiple potentially expensive bulk samples. Nanoindentation is fast, almost non-destructive, and requires only a single sample, to which large numbers of indents can be applied. Furthermore, nanoindentation is widely applicable, even to materials that are too brittle for traditional compression tests. Here, we show that nanoindentation is sufficient for extracting much of the same information that is measured in traditional sample compression tests in metallic glasses. The dynamics and statistics of the plasticity of two types of metallic …

An Efficient Self-Supervised Learning Framework For Swarm Robot Trajectory Analysis, Brooklyn Berry, Gaukhar Nurbek, Juan Manuel Perez, Richard Tapia, Qi Lu, Yifeng Gao

Computer Science Faculty Publications

Swarm robotics leverages groups of autonomous robots to perform complex tasks collaboratively. Recently, there has been growing interest in the Self-Supervised Learning framework (SSL) for social robots, yet very little research has been done on designing a SSL framework for foraging swarm robots systems. In this paper, to address the two challenges above, we proposed a novel efficient self-supervised learning framework. Specifically, we proposed 1) a shared weight multi-instance based encoder-decoder structure for model pre-training; and 2) an embedding series compression strategy to reduce the space cost in inference stage. Experiments show our system can match the performance of standard …

How Fair Workweek Laws Affect Labor Markets: A New York City Case Study, Joseph Pickens, Aaron Sojourner

Employment Research Newsletter

No abstract provided.

Re: 3rd Quarter 2025 – Interim Site-Wide Surface Water Monitoring Data Report Silver Bow Creek Butte Area Npl Site, Butte Priority Soils Operable Unit Consent Decree-Civil Action No. Cv 89-039-Bu-She, Josh Bryson

Silver Bow Creek/Butte Area Superfund Site

No abstract provided.

Direct And Indirect Effects Of Water-Table Levels On Redox-Active Organic Matter Reduction In An Alaskan Rich Fen, J. E. Rush, E. S. Kane, Jason K. Keller, J. C. Bowen, Cassandra A. Zalman, E. S. Euskirchen, K. H. Wyatt, A. R. Rober, E. S. Hinckley

Biology, Chemistry, and Environmental Sciences Faculty Articles and Research

Redox-active organic matter (RAOM) reduction is an important control on methane production in northern peatlands, but it is unclear how global climate change will affect RAOM reduction. We investigated the effects of water-table levels on RAOM reduction by leveraging a long-term water-table manipulation experiment in an Alaskan fen, which includes Lowered and Raised treatment plots relative to a Control. Common substrate peat was incubated in each plot during one summer of experimental manipulation and another summer of site-wide flooding. During experimental manipulation, common substrate RAOM was more reduced in the Raised plot than the Lowered plot at both 10–20 cm …

Versatile Nitration Of Bodipy Dyes Using No₂Bf₄: Effects Of Nitro Substituents On Spectroscopic And Self-Assembly Properties, Caroline Sarange Gwaro

LSU Master's Theses

This study explores the regioselective nitration of BODIPY dyes at the 2, 3- and 2,6-positions using nitronium tetrafluoroborate (NO₂BF₄), offering a high-yielding and mild synthetic route. The introduction of nitro groups significantly alters the dyes’ photophysical and self-assembly properties. Mono-nitrated BODIPYs exhibit hypsochromic shifts in absorption and emission spectra, increased dipole moments, enhanced Stokes shifts, and reduced molar absorptivity. In contrast, di-nitrated analogs show bathochromic shifts and decreased dipole moments in both ground and excited states. Spectroscopic characterization was performed using UV-vis and fluorescence spectroscopy, supported by density functional theory (DFT) calculations. Self-assembly behavior was investigated in polar (acetonitrile) and …

Establishing A Framework Of Best Management Practices For Sustainable Water Quality: Integration Of Technology And Remote Sensing, Mason L. Marcantel

LSU Master's Theses

Water quality security is a complex management issue that is constantly challenged by factors of seasonal variability in climate change, urban population growth, and agricultural intensification. These factors warrant the need for innovative technological adaptations to management practices that integrate remote monitoring, predictive modeling, and sustainable resource utilization. This study establishes a framework for sustainable water quality practices through the integration of remote sensing technology for urban wastewater treatment and agricultural irrigation systems. This dual-site research study explores seasonal water quality dynamics and technological interventions to create a more proactive approach to water quality security.

In the first study, water …

Causal Predictive Modeling Of Survival Of Lung And Bronchus Cancer Patients Diagnosed During 2010–2011 In Texas, Zeinab Mohamed, Sidketa Fofana, Everardo Cobos, Manish K. Tripathi, Tamer Oraby

School of Mathematical & Statistical Sciences Faculty Publications

Background: Lung and Bronchus cancer is the most fatal type of cancer in the United States. According to the American Cancer Society, there were more than 127,000 deaths from lung cancer in 2023. Lung cancer care cost 23.8 billion dollars in 2020. In Texas, only 22.8% of lung cancer patients survived 5 years or more past diagnosis based on 2012-2018 data.

Aim: This study evaluates the survival length of lung and bronchus cancer patients in Texas using advanced statistical and machine learning methods applied to an 11-year cohort study from Surveillance, Epidemiology, and End Results Program. It also quantifies the …

Quantum Leap: Harnessing Quantum–Ai Synergy For Resilient Supply Chains And Predictive Routing Under Tariff Shocks, Andrew Burnstine, Raouf Ghattas

Faculty and Staff Publications & Presentations

No abstract provided.

Investigating The Impacts Of Microplastics On Bacterial Community Dynamics In Mangrove Sediments, Al Maha Sulaiman Alshamsi

Thesis/ Dissertation Defenses

Microplastic (MP) pollution poses a growing threat to global ecosystems, particularly in coastal habitats like mangroves, which serve as vital carbon sinks. This study investigates the specific impacts of polypropylene (PP), polyethylene terephthalate (PET), and adipic acid (AA) on microbial community assembly in mangrove sediments, with a focus on sequential arrival of different MPs. Based on MP identity, early arrival of specific MP before others can significantly impact microbial community composition and their functioning. However, the impacts of the sequential arrival of MPs on microbial communities have never been studied. This research fills this important knowledge gap by using novel …