Digital Commons Network^™

Automatically Constructed Preference Pairs For Chain-Of-Thought: Consistency Gains With Accuracy Tradeoffs, Cameron Scolari, Lanyu Shang

Honors Thesis

We investigate preference optimization over chain-of-thought (CoT) reasoning using automatically constructed preference signals derived from the accuracy and internal consistency of a model. Our results show that framing reasoning as a preference learning problem improves both the accuracy of the final answer and the structure of the model outputs. We observe a non-monotonic relationship between performance and the Direct Preference Optimization (DPO) scaling parameter β, where moderate values maximize accuracy while lower values improve stability, highlighting a tradeoff between optimization strength and reliable generation. We further identify a tradeoff between reasoning consistency and accuracy. Increasing the consistency weight improves agreement …

A Governance-Aware Multi-Agent Framework For Enhancing Fairness & Temporal Accuracy In Disaster Response Systems, Md. Ashfaqur Rahman

Theses and Dissertations

Large Language Models (LLMs) have demonstrated significant potential in disaster-response decision support, however, their deployment in high-stakes humanitarian settings raises critical concerns regarding factual reliability, fairness, temporal validity, and governance compliance. Hallucinated outputs, demographic bias, and outdated recommendations can directly impact vulnerable populations and undermine public trust. This dissertation proposes a governance-aware multi-agent framework designed to enhance fairness and temporal accuracy in disaster-response systems through structured Retrieval-Augmented Generation (RAG), verification-driven orchestration, and adaptive correction mechanisms.The proposed architecture decomposes response generation into specialized agents responsible for real-time retrieval, fact-checking, bias auditing, temporal validation, threshold-based correction, and monitoring. By embedding governance constraints …

A Socio-Computational Framework For Understanding Information Campaigns Through A Collective Action Perspective, Sayantan Bhattacharya

Theses and Dissertations

In a time when social media significantly influences public dialogue, grasping the elements that contribute to the success of information campaigns has become vital for understanding modern social movements and political engagement. This dissertation explores the essential factors that affect the efficacy of information campaigns across digital platforms, addressing a notable gap in existing research that frequently neglects the systematic connection between information spread and outcomes of collective action. Instead of viewing these as distinct phenomena, this study constructs an integrated framework that highlights three crucial dimensions of successful information campaigns: the human factor, which emphasizes the role of influential …

What History Shows: A Structural Account Of Fixed-Point Theory Formation, Griselda Poe

Publications and Research

Theory generation has long been subsumed under categories such as creativity, genius, and innovation. These categories do not distinguish assembly-based conceptual synthesis from fixed-point theory generation.

This paper makes that distinction explicit. The termination condition of assembly is external: data, citation, endorsement, usability. The termination condition of fixed-point theory generation is internal: consistency with internally held constraints, resolution of structural contradiction. The two operate under different processing conditions.

The historical record confirms this distinction. What Darwin, Einstein, Spinoza, and Kant produced was not assembly. Their processes involved unresolved branch retention and decomposition necessity, arriving at internally constrained fixed-point termination. Freud …

Improving Semantic Precision In Text-To-Image Diffusion Models Via Latent-Space Optimization And Semantically-Parsed Evaluation, Mohammad Rouie Miab

McKelvey School of Engineering Graduate Student Theses & Dissertations

Text-to-image diffusion models can produce visually impressive images from natural-language prompts, but they often fail to satisfy the detailed semantic constraints expressed in compositional prompts. Typical failure modes include omitted objects, merged entities, incorrect quantities, incorrect attribute binding, and leakage of one entity's attributes onto another. This thesis studies the problem of semantic precision in text-to-image generation: how faithfully a generated image satisfies the structured meaning of its prompt.   The thesis makes two linked contributions. First, it presents a training-free inference-time refinement method for diffusion-based image generation. The method operates directly in latent space during denoising and uses noun-phrase-aware cross-attention …

Interpreting American Sign Language: A Literature Review Of Assistive Technologies, Natalie Louise Paradiso, Emma Grace Kochenderfer

Student Scholar Symposium Abstracts and Posters

American Sign Language (ASL) is a visually elaborate, spatially oriented linguistic methodology that relies on combinations of hand movements, body positioning, facial expressions, and motion/spatial perception, aspects of which make interpretation difficult for automated machine recognition. Current assistive technology approaches to ASL interpretation are generally within the categories of computer vision models (including deep learning, multi-focus image fusion, and keypoint tracking) and wearable, multimodal/sensor-based approaches (such as smart glasses and inertial-sensor gloves). Within controlled environments, computer vision models perform well. However, when applied to conditions such as non-manual signs/features, signer variability, and rapid assimilation, they falter in processing all aspects …

Propasafe-Hybrid: A Text-Based Hybrid Propaganda Detection Tool, Thomas Kimmeth, Avijit Roy, Vivek Sharma

Publications and Research

Propagandistic content increasingly circulates through online news and social media, where readers often encounter it with limited scrutiny, highlighting the need for reliable and fine-grained detection. This paper introduces Propasafe-Hybrid, a sentence-level system that integrates a fine-tuned transformer classifier with LLM-based technique classification to identify, label, and explain specific propaganda strategies. The pipeline generates actionable outputs, including highlighted sentences, technique assignments, and concise rationales, so users can immediately understand why a sentence was flagged and how each label was determined. To control inference cost, Propasafe-Hybrid employs a cost-aware pre-filtering stage that forwards only high-likelihood sentences to LLMs, reducing token usage …

Faircarenlp: An Ai-Driven Patient Review Analyzer For Healthcare, Sayyed Mohammad Pourya Momtaz Esfahani, Davey Seeman, Christoffer Dharma, Mohammad Noaeen, Shion Guha, Zahra Shakeri

Health Services and Informatics Research

Objective

To develop and evaluate an automatic patient review analyzer that applies advanced Natural Language Processing (NLP) and machine learning methods to improve the efficiency, fairness, and accuracy of healthcare feedback analysis.

Materials and methods

We designed a multi-component pipeline incorporating sentiment analysis, key theme extraction, clinical Named Entity Recognition (NER), and fairness modules. Bias mitigation was addressed through the integration of three complementary approaches: adversarial debiasing, Hard Debiasing, and Iterative Null-space Projection (INLP). Multiple BERT-based models (DistilBERT, BioBERT, RoBERTa-base, BERT-base-uncased) were trained and evaluated under varying hyperparameters and fairness/adversarial loss configurations. Model performance was assessed using accuracy, F1, recall, …

Automated Analysis Of Radiation Oncology Incident Reports Using Large Language Models, Nathan A. Dobranski

LSU Master's Theses

Patient safety incident reporting in radiation oncology requires expert analysis that is time-intensive and subject to variability. This thesis presents the development and technical validation of a locally deployed large language model (LLM) system for automated incident report analysis across multiple cancer centers. The system was designed for automated summarization and taxonomy assignment of Radiation Oncology Incident Learning System (RO-ILS) reports, operating entirely on local infrastructure to preserve patient privacy. A two-round, multi-rater evaluation methodology was employed, incorporating 600 total expert evaluations from two academic cancer centers. Round 1 established baseline performance using Mistral 7B and Mixtral 8x7B models with …

Propasafe-Hybrid: A Text-Based Hybrid Propaganda Detection Tool (Ila 2026 Presentation), Thomas Kimmeth, Avijit Roy, Vivek Sharma

Publications and Research

This presentation introduces Propasafe-Hybrid, a hybrid system for sentence-level propaganda detection that combines offline transformer-based classification with selective large language model (LLM) explainability. The system employs a two-stage pipeline in which a local BERT-based classifier evaluates all input text and filters non-propagandistic content, while only high-confidence candidates are forwarded to an LLM for rhetorical technique labeling and explanation. This design enables cost-aware, privacy-conscious, and scalable analysis by reducing unnecessary reliance on external models.

Propasafe-Hybrid identifies propagandistic techniques such as loaded language, obfuscation, and appeal to fear, and generates concise natural language rationales that make these techniques interpretable to users. By …

Research On Text Translation Model Based On Large Language Model And Knowledge Enhancement Framework, Chuanming Yu, Haoxuan Li

Journal of Scientific Information Research

[Purpose/significance] This paper aims to improve the translation quality of large language models and effectively alleviate the translation illusion problem, thereby enhancing cross-linguistic information retrieval capabilities. [Method/process] A translation generation method based on a knowledge enhancement framework is proposed. This framework optimizes the translation process from multiple dimensions, such as style, focus, and cultural adaptability, by combining external knowledge provided by the translation context building module and the knowledge base building and retrieval module, and then utilizing the guidance of the text attention module. [Result/conclusion] Experimental results show that the proposed method effectively enhances model performance. Specifically, on the WikiLingua, …

Perspectives On Interpretability For Neural Text Representations, Jia Peng Lim

Dissertations and Theses Collection (Open Access)

In this dissertation, we investigate interpretability in the three elements of learning neural text representations: inputs, passed into models, to produce probabilistic outputs. We emphasise perspectives as we present alternative novel methods to mine and organise meaning in this work.

Models. We initiate our investigation by examining Neural Topic Models (NTM), proposing an alternate angle of interpreting its word-topic distribution, producing better topic representations for interpretation. Our method maps the problem of finding these better interpretations to classical NP-hard graph problems, enabling examination of topic distributions in a composite manner. Next, we apply our previous findings to extract interpretations from …

Towards Multi-Hop Retrieval Using Bipartite Question-Oriented Graphs, Micah Mccollum

Electrical Engineering and Computer Science Undergraduate Honors Theses

Accurately answering multi-hop questions requires full retrieval of multiple, interdependent passages and is a long-standing problem in the area of natural language question answering (QA). While retrieval-augmented generation (RAG) helps address single-hop questions, many retrievers presently focus on semantic similarity in a dense vector space, which is insufficient for handling multi-hop questions specifically. To ameliorate this, we propose constructing a bipartite question- oriented graph composed of hypothetically generated questions connected to passages at index time. The construction of the graph is guided by a large language model (LLM) to prioritize the formation of edges that signal whether a question can …

Robustness Of Vision Language Models For Pedestrian Detection Tasks, Ostonya K. Thomas

All Theses

Autonomous vehicle (AV) systems typically employ modular systems in which discrete components handle separate tasks such as perception, computation, and path planning. While flexible, this approach allows errors to propagate and compound across the pipeline, and many AI systems offer little transparency into their internal decision-making. Such limitations are particularly concerning in safety-critical domains where failures can carry lethal consequences. Vision Language Models (VLMs) have emerged as a promising alternative because they support end-to-end implementations that bypass compounding error risks and provide natural language explanations of their outputs. Despite these advantages, prior research has demonstrated that both computer vision systems …

Processing Conditions In Narrative Interpretation: A Structural Account Of Cf/Ef Divergence In "The Clerk's Tale”, Griselda Poe

Publications and Research

This paper applies the framework established in Paper 19, "Cognition Is Not Content: A Structural Account of Processing Conditions," to re-describe Chaucer's "The Clerk's Tale" from The Canterbury Tales.

The same narrative produces two incompatible interpretations: a record of domestic violence, and a story of genuine love. This divergence does not arise from differences in ethical judgment or emotional response. It arises from structural differences in the conditions under which information is reconstructed.

This paper does three things. First, it analyzes the characters Walter and Griselda in terms of CF (Core-foregrounded) and EF (Modulation-foregrounded) processing conditions. Second, it describes …

Beyond The Interface: Human Perceptions Of Generative-Ai Chatbots As Conversational Partners, Browning W.E. Blair

All Theses

Generative AI (gen-AI) chatbots are becoming embedded in everyday communicative life, yet it remains unclear whether users perceive these systems as socially reciprocative conversational partners. Therefore, this study examines how young adults understand and interact with gen-AI chatbots, focusing on perceptions of conversational partnership, anthropomorphism, politeness, discomfort, and technical understanding. Guided by the CASA framework, Media Equation Theory, and the uncanny valley hypothesis, this study employed four semi-structured, online focus groups with 15 undergraduate students and recent college graduates in the United States. Findings indicate that participants did not broadly perceive gen-AI chatbots as conversational partners in the interpersonal sense. …

Autonomous Deficiency Detection And Vision-Language Summarization For Underground Infrastructure On Embedded Edge Systems, Johny Lopez

LSU New Orleans Theses and Dissertations

Aging underground infrastructure poses significant risks to public health and environmental safety, yet structural condition assessment remains bottlenecked by labor-intensive manual CCTV inspections. This thesis proposes a comprehensive algorithmic framework enabling fully autonomous, real-time deficiency detection, geometric assessment, and natural language reporting on resource- constrained edge computing platforms. Three core components address this challenge. First, RAPID-SCAN, a novel semantic segmentation architecture utilizing a Dynamic Feature Pyramid Network and Channel-Spatial Attention, achieves real-time, pixel-precise defect localization with dramatically reduced parameters. Second, an Edge-Optimized Vision-Language Model pipeline employing LoRA and 4-bit QLoRA quantization compresses Phi-3.5 for local deployment, en- abling autonomous technical …

Genre Prediction Using Rnns And Llm-Enhanced Video Game Review Data, Gabriel Young

Graduate Theses and Dissertations

LLMs (Large Language Models) are powerful tools for engaging with textual data, carrying many advantages over classical NLP (Natural Language Processing) and ML (Machine Learning) approaches. However, a classical ML model can still be faster, more efficient to run, and accessible than an LLM. We seek to gain the benefits of LLM text comprehension and preserve them in a classical ML model, a hybrid approach. The LLM operates on text to surface relevant information and associations in our problem space, then the ML model trains on the LLM output. The model may learn from the LLM and provide a more …

Improving Online Political Discussion With Automated Bot Intervention, Bethanie E. Hackett

Departmental Honors & Graduate Capstone Projects

The quality of political discussions occurring on online platforms or social media sites has been deemed quite poor. To address this issue, I investigated whether a Large Language Model (LLM) can be used to promote civil and productive political discussions by identifying and responding to unproductive dialogue. I fine-tuned an existing LLM to detect elements of problematic dialogue, namely misinformation, misrepresentation of sources, logical fallacies, bias, and toxic language, and then respond in a corrective yet non-confrontational manner. The resulting model is referred to as FroBot and was evaluated through an experiment in which a human participant was placed in …

Utilizing Brain Computer Interfaces That Interact With A Virtual Keyboard, Skye Lilienthal

Honors Theses

A brain-computer interface (BCI) can allow someone to utilize electrical signals in their brain to complete tasks using a computer. BCIs can help people take advantage of technology to type without the need for a traditional keyboard setup. This paper used the OpenBCI Mark IV to test the effectiveness of non-invasive BCIs with dry electrodes within the OpenViBE P300 Speller. This paper shows how to use the P300 speller through a setup pipeline. Results indicate that electrode placement affects P300 accuracy and that areas related to visual processing improve accuracy, suggesting that P300 signals can be detected within OpenBCI Mark …

You Can’T Spell Audit Without Ai: The Current Uses Of Artificial Intelligence In Audit, Jena Perkins

Senior Honors Theses

The accounting profession continuously adapts to the innovations provided by the broader context in which it exists. Artificial intelligence (AI) is a forerunner among tools used to enhance and optimize auditing services within the accounting profession. The realm of AI offers advancements to procedures used within an audit to detect misstatements. Based on the proprietary platforms developed by Big 4 accounting firms, AI is a key component in maintaining an advanced approach towards auditing.

Public Health Responsible Ai Capability (Ph-Raic) Framework: A Conceptual Model For Integrating Ai Into Public Health Agencies, Arnob Zahid, Ravishankar Sharma, Rezwan Ahmed

All Works

Background: Artificial intelligence (AI) is transitioning from experimental pilots to core public health functions such as disease surveillance, resource planning, and analysis of social and structural determinants of health. Yet, health data collection and stewardship remain fragmented across the globe; some jurisdictions still rely on paper-based systems, while others operate noninteroperable digital systems that can exacerbate inequities. Treating health data as a global good therefore requires governance that enables innovation while protecting rights, safety, and trust. This study aims to develop a conceptual meso-level capability framework that translates responsible AI principles into organizational practices for public health agencies. Methods: We …

The Application Of Natural Language Processing Towards Auditing Of Unstructured Data: A Design Science Approach, Dennis K. Amoatey

Electronic Theses and Dissertations

Financial auditors must manually review large volumes of unstructured text that may include contracts, internal policies, footnotes, and journal entry descriptions. This time-intensive process introduces risk of human error and inconsistency. Despite advances in automation, no systematic approach exists for applying Natural Language Processing (NLP) to this problem at scale. Using a design science approach, this study develops a framework that demonstrates how NLP techniques can be incorporated across key phases in the audit process, including planning, internal controls evaluation, evidence gathering, and reporting. Initial evaluation through expert feedback had a mix of responses. While some argued difficulty with data …

Sevoauth: Secure Voiceprint Authentication With Hash-Based Feature Transformation, Rui Zhang, Zheng Yan, Robert H. Deng

Research Collection School Of Computing and Information Systems

While voiceprint authentication offers convenient user authentication and access control through voice feature recognition, a critical research gap remains: existing voiceprint authentication systems fail to simultaneously achieve sound security against replay, spoofing, and adversarial attacks, preserve voice privacy leakage, and satisfy usability demand. Previous efforts have struggled to balance these issues comprehensively. To bridge this gap, we present SeVoAuth, a cloud-based Voiceprint Authentication as a Service (VAaaS) system designed to provide privacy preservation, robust security, and enhanced usability. SeVoAuth stores a synthesized voiceprint of a user in the cloud during user registration, thereby safeguarding the privacy of the real voiceprint …

Synthesis And Evaluation Of Long-Term History-Aware Medical Dialogue, Hebin Hu, Renke Dai, Ah-Hwee Tan, Yilin Kang

Research Collection School Of Computing and Information Systems

An effective healthcare agent must be able to recall and reason over a patient’s longitudinal medical history. However, the absence of datasets with realistic long-term dialogue timelines limits systematic evaluation. Real clinical text is constrained by privacy and ethics, while existing benchmarks focus on isolated interactions, failing to capture cross-session reasoning. We introduce a framework for synthesizing high-quality, long-term medical dialogues with LLMs. Our approach entails a knowledge-guided decomposition into three stages: constructing synthetic patient profiles with diverse disease and complication trajectories, generating multiturn dialogues per encounter, and integrating them into a coherent longitudinal history dataset, MediLongChat. We establish three …

Analyzing The Writing Style Of Generative Ai When Prompted With Writing Samples, Samuel Mcdowell

Senior Honors Theses

Authorship attribution is an important topic in today’s world of Large Language Models (LLMs). It is the technology that helps to verify the author of a written work. This study explores whether LLMs can successfully mimic an individual’s writing style if they are given a text sample. A dataset of human-written texts was collected and used to prompt several LLMs to generate new texts that attempt to replicate the original author’s stylistic characteristics. The generated texts were then tested with modern authorship attribution models to determine whether they would be identified as being written by the original author. The results …

Volume 17, Christian O’Neill, Kyara Greene, Savva Sidorov, Laura Bisaillon, Luke Clemmer, Hannah Gordon, Kitt Benson, Taylor Blount, Rachel Danzitz, Nicholas Duellman, Chase Gionis, Hima Fernando, Seth Franzyshen, Onyx Gonzalez, Bryan Lin, Samantha Start, Ysabel Wells, Maggie Duncan

Incite: The Journal of Undergraduate Scholarship

Introduction Dr. Amorette Barber, Director, Office of Student Research

From the Editor Dr. Hannah Dudley-Shotwell

Cover Artist’s Statement Maggie Duncan

On Mentoring Dr. Yulia Uryadova

Ukrainian Resistance in the Face of Russification: Nestor Makhno and Anarchism

by Christian O’Neill

Life Vest by Kyara Greene

Isolation and 16S rRNA Identification of Bacteria from Fire Department Connection Pipe by Savva Sidorov

The Effectiveness of Planned Exercise in Reducing ADHD Symptoms in Children by Laura Bisaillon & Luke Clemmer

Linguistic Analysis on Confidence and Communication Strategies with Disparities Between Sign Fluency and Hearing Impairment by Hannah Gordon

Freedmen in Indian Territory by Kitt …

Advancing Context-Aware Detection Of Socially Harmful Discourse Using Transformer-Based Models, Santosh Chapagain

All Graduate Theses and Dissertations, Fall 2023 to Present

Social media platforms are a central part of modern communication, shaping how people share ideas, build communities, and discuss social issues. While these spaces can support connection and self expression, they also enable the spread of harmful language such as hate speech. At the same time, social media is an important place where members of marginalized communities, including sexual and gender minorities, express stress, discrimination, and emotional challenges in ways that are often indirect and context dependent.

This research examines whether modern artificial intelligence systems can better identify harmful language and expressions of minority stress in online posts. The study …

Large Language Models For Introductory Computer Science Education: Content Generation, Intelligent Tutoring, And Learner Modeling, Muhammad Fawad Akbar Khan

All Graduate Theses and Dissertations, Fall 2023 to Present

This dissertation studies how artificial intelligence, especially large language models such as GPT, can help students learn introductory computer programming when the models are used inside a carefully designed learning system. Instead of focusing on AI as a standalone tool, the dissertation follows a connected story: generating learning resources, building a tutoring platform, running a user study, and then analyzing how students behave while they program.

The work first uses prompt engineering to create a large collection of 11,700 Python exercises aligned with introductory computer science topics. Students and instructors then evaluate these exercises to check whether they are clear, …

Probing Representational Emergence In Large Language Models, Shawn Ismail

Master's Theses

This thesis investigates whether abrupt behavioral gains in large language models under scaling are accompanied by systematic changes in internal representations. It combines a behavioral screen of 65 tasks per family with targeted layerwise probing across eight decoder-only, open-weight model families. Behavioral emergence is defined for each family-task trajectory using an empirical jump detector, with segmented regression retained only as a diagnostic. The representational follow-up analyzes 27 selected MMLU subtasks shared across all families, spanning 37 checkpoints and 216 family-task units.

For each follow-up checkpoint, frozen linear probes are trained on every layer's hidden states to measure how much task-relevant …