Artificial Intelligence and Robotics Commons^™

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 …

Machine Learning For Handwritten Character Recognition, Hannah Freitag

Honors Capstones

Handwritten character recognition remains a challenging problem in machine learning due to the high variability of handwriting across individuals and the visual similarity between certain character classes. This project explores whether Singular Value Decomposition (SVD)-based dimensionality reduction can serve as an effective preprocessing step for a fully connected neural network trained on the EMNIST Balanced dataset, a 47-class benchmark of handwritten digits and letters. By projecting 784- dimensional pixel inputs onto the top 70 principal components, approximately 90% of the total variance is preserved while reducing input dimensionality by 91%. The resulting SVD-based model achieves approximately 94% test accuracy, outperforming …

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 …

A Survey On Knowledge-Enhanced Healthcare Question Answering Systems, Junnan Su, Pu Han, Jianxiang Wei

Journal of Scientific Information Research

[Purpose/significance] This paper aims to review the research progress and applications of knowledge enhancement techniques in healthcare question answering systems, in response to the limitations of traditional systems in knowledge representation and reasoning, as well as challenges faced by current large language model-based systems, such as insufficient domain knowledge, privacy concerns, and hallucination. The review provides a systematic reference for improving the precision and knowledge reliability of such systems. [Process/method] Focusing on knowledge enhancement strategies, this paper firstly outlines their fundamental concepts and overall framework. The strategies are then categorized into explicit and implicit types, with an analysis of their …

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, …

Sequential Robustness In Adversarial Reinforcement Learning, Roman Lok-Ming Belaire

Dissertations and Theses Collection (Open Access)

My goal is to build autonomous systems that expand the reach of human capability in challenging domains such as undersea and space exploration, disaster response, and large-scale infrastructure. In everyday settings, these systems will increasingly appear in safety-critical applications such as autonomous driving, robotics, and industrial manufacturing. A central requirement for these systems is the ability to operate reliably under uncertainty, particularly when the environment behaves in unanticipated ways.

The robust handling of unforeseen environment dynamics is therefore a technical cornerstone of autonomous decision-making; Adversarial attacks provide a useful and principled lens through which to study this problem. Adversarial \textit{robustness}, …

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 …

Sql Query Optimization - Human Vs. Chatgpt, Hailey Dennis

All Graduate Reports and Creative Projects, Fall 2023 to Present

Large Language Models (LLMs) such as ChatGPT have become ubiquitous tools for working professionals in the software industry. Many engineers are finding new ways to increase productivity by offloading tasks onto LLMs, while others are finding it difficult to trust code produced artificially, even after review. Taking a look at both perspectives, this study aims to compare a human’s ability to optimize SQL queries to that of an LLM and assess the experience using both methods.

Manual query optimization is a tedious task that relies heavily on statistics, heuristics, and good intuition. The SQL developer must search for the optimal …

Pyspqr: A Python Package For Density Estimation Using Deep Learning, Cameron Eddy, Reetam Majumder

Electrical Engineering and Computer Science Undergraduate Honors Theses

Splines are used for representing complex functions. In statistics, splines can be used for distributional shapes that are difficult to model by traditional parametric approaches. Ramsay (1) uses M-Spline bases to estimate continuous distributions. Semi-Parametric Quantile Regression (SPQR), developed by Xu and Reich (2), models conditional distributions where a neural network is used to estimate the basis function weights that depend on covariates. (3) implements a package for SPQR in R. We build on this by implementing a version of SPQR in Python with PyTorch. By using PyTorch, we can use more sophisticated deep learning architectures than those available in …

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 …

​Autonomous Agentic Orchestration For Physics-Aware Scientific Discovery: An Integrative Multimodal Framework For 2d Material Characterization​, Sankalp Pandey

Electrical Engineering and Computer Science Undergraduate Honors Theses

The advancement of next-generation semiconductor and quantum technologies relies on the scalability of the fabrication of two-dimensional (2D) van der Waals heterostructures. However, this process is severely bottlenecked by characterization workflows. Optical microscopy provides high-throughput imaging of 2D material flakes, but lacks the explicit physical priors required for the discernment of sub-nanometer thickness variations, such as distinguishing monolayers from bilayers. The use of computer vision models to automate the localization and characterization process of the flakes was proposed. As a part of this effort, we develop QuantumFlake, an open-source framework to streamline the integration and deployment of computer vision models …

Datapeer: A Hybrid Interaction Model Web Application Integrating Llms For Human–Llm Collaboration In Data Analysis And Exploration, William I. Bumcum

Honors Theses

DataPeer is a web application that combines open-ended high agency (OHA) and structured low-agency (SLA) interaction paradigms to support human-LLM collaboration in exploratory data analysis. DataPeer integrates a large language model (LLM) with a React frontend and FastAPI backend, allowing both qualitative and quantitative analysis of user-uploaded CSV datasets through a chat-based interface. Users can attach datasets and provide natural language queries, while the LLM provides data analysis to the user. This thesis investigates the integration of LLMs into data analysis workflows and addresses gaps in interaction design and user agency in LLM-driven data tools by offering a responsive interface …

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 …

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 …

Mease: Multi-Agent Episodic Action Sequence Explanation, Phyo Wai Khaing, Minghong Geng, Shubham Pateria, Budhitama Subagdja, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Multi-agent reinforcement learning (MARL) achieves remarkable performance in complex coordination tasks, yet interpreting the emergent behaviors of trained agents remains a fundamental challenge. Most current explainability methods focus on individual agent decisions, overlooking the critical interplay of joint strategiesand temporal coordination patterns that define successful multi-agent policies. We present MEASE (Multi-agent Episodic Action Sequence Explanation), a novel explainable MARL (XMARL) framework that explains trained MARL policies as human-interpretable emergent cooperative joint behaviors. MEASE employs a cognition-inspired episodic memory model to learn spatio-temporal multi-agent interaction patterns, coupled with abstraction algorithms that identify significant cooperative agent behaviors. We evaluate MEASE on diverse …

Market Reactions To Deceptive Language In Fake News: Implications From Language Expectancy Theory And Transfer Learning, Ka Chung Ng, Ping Fan Ke, Ping Fan, Mike So, Tam, Kar Yan

Research Collection School Of Computing and Information Systems

The advent of generative artificial intelligence (AI) has heightened the proliferation of fake news. A key challenge is the limited real-world data to investigate the societal impact of fake news produced by generative AI. In this paper, we examine stock market reactions to financial news articles that exhibit stylometric similarity to human-crafted and AI-crafted fake financial news. Grounded in language expectancy theory, we employ a style-based transfer learning model, pre-trained to recognizing deceptive language employed in various types of fake news intricacies. We then apply this model to a comprehensive dataset of financial news, assigning a “veracity style score” to …

Fighting Against Recruitment Scams: Theory-Driven Supervised Learning And Empirical Analysis For Digital Fraudulent Recruitment Posting Behavior, Tom (Tianteng) Wang, David (Jingjun) Xu, Keng Siau, Zhongju (John) Zhang

Research Collection School Of Computing and Information Systems

The number of recruitment postings on digital recruitment hiring platforms has increased since the COVID-19 pandemic. However, the weak surveillance and operations of these platforms, combined with the fact that most job seekers have relatively low vigilance and a strong desire for recruitment offers, enable scammers to easily deceive job seekers for their money and confidential information. In this work, we combine prevailing text mining techniques (i.e., ChatGPT with prompting engineering and supervised machine learning) with interpersonal deception theory (IDT) from social science to design an interpretable IT system to predict fraudulent recruitment postings on digital recruitment-hiring platforms. We compare …

Enhancing Action And Ingredient Modeling For Semantically Grounded Recipe Generation, Guoshan Liu, Bin Zhu, Yian Li, Jingjing Chen, Chong-Wah Ngo, Yu-Gang Jiang

Research Collection School Of Computing and Information Systems

Recent advances in Multimodal Large Language Models (MLMMs) have enabled recipe generation from food images, yet outputs often contain semantically incorrect actions or ingredients despite high lexical scores (e.g., BLEU, ROUGE). To address this gap, we propose a semantically grounded framework that predicts and validates actions and ingredients as internal context for instruction generation. Our two-stage pipeline combines supervised fine-tuning (SFT) with reinforcement fine-tuning (RFT): SFT builds foundational accuracy using an Action-Reasoning dataset and ingredient corpus, while RFT employs frequency-aware rewards to improve long-tail action prediction and ingredient generalization. A Semantic Confidence Scoring and Rectification (SCSR) module further filters and …

Benchmarking Gaslighting Attacks Against Speech Large Language Models, Jinyang Wu, Bin Zhu, Xiandong Zou, Qiquan Zhang

PhD Student’s Publications Collection

As Speech Large Language Models (Speech LLMs) become increasingly integrated into voice-based applications, ensuring their robustness against manipulative or adversarial input becomes critical. Although prior work has studied adversarial attacks in text-based LLMs and vision-language models, the unique cognitive and perceptual challenges of speech-based interaction remain underexplored. In contrast, speech presents inherent ambiguity, continuity, and perceptual diversity, which make adversarial attacks more difficult to detect. In this paper, we introduce gaslighting attacks, strategically crafted prompts designed to mislead, override, or distort model reasoning as a means to evaluate the vulnerability of Speech LLMs. Specifically, we construct five manipulation strategies: Anger, …

Teacher-Student Diffusion Model For Text-Driven 3d Hand Motion Generation, Ching Lam Cheng, Bin Zhu, Shengfeng He

PhD Student’s Publications Collection

Generating realistic 3D hand motion from natural language is vital for VR, robotics, and human-computer interaction. Existing methods either focus on full-body motion, overlooking detailed hand gestures, or require explicit 3D object meshes, limiting generality. We propose TSHaMo, a model-agnostic teacher-student diffusion framework for text-driven hand motion generation. The student model learns to synthesize motions from text alone, while the teacher leverages auxiliary signals (e.g., MANO parameters) to provide structured guidance during training. A co-training strategy enables the student to benefit from the teacher’s intermediate predictions while remaining text-only at inference. Evaluated using two diffusion backbones on GRAB and H2O, …