Artificial Intelligence and Robotics Commons^™

Revitalization Of Endangered Languages With Ai, Ivory Yang

Dartmouth College Master’s Theses

The preservation and revitalization of endangered languages, particularly those with minimal digital presence, presents significant challenges for computational linguistics. This thesis addresses these challenges by proposing novel methods for language identification and data generation, focusing on underrepresented Indigenous languages, specifically Nüshu, Native American and Native Alaskan languages.

In the first study, a COLING 2025 paper, we present NüshuRescue, an AI-driven framework designed to facilitate the preservation of Nüshu, an endangered script used exclusively by Yao women in China. Using minimal seed data, we demonstrate how GPT-4-Turbo can generate new translations, expanding a publicly available Nüshu-Chinese corpus, achieving 48.69% accuracy in …

Diversity-Augmented Training For Generalizable Ai Agents, Wenjun Li

Dissertations and Theses Collection (Open Access)

Deep Reinforcement Learning (RL) has achieved remarkable success over the past decade, from superhuman performance in video games to real-world applications like robotics. However, RL models often lack generalization, making them unreliable when deployed in unfamiliar scenarios. For example, robots must adapt to varying terrains with different slopes and obstacles, yet standard RL training does not explicitly promote such adaptability. While various methods have been proposed to enhance RL robustness, achieving reliable generalization remains an open challenge.

This dissertation focuses on improving the generalization capability of agents in three major settings: infinite horizon RL agents, finite horizon RL agents, and …

“Ronaldo’S A Poser!”: How The Use Of Generative Ai Shapes Debates In Online Forums, Yuhan Zeng, Yingxuan Shi, Xuehan Huang, Fiona Fui-Hoon Nah, Ray Lc

Research Collection School Of Computing and Information Systems

Online debates can enhance critical thinking but may escalate into hostile attacks. As humans are increasingly reliant on Generative AI (GenAI) in writing tasks, we need to understand how people utilize GenAI in online debates. To examine the patterns of writing behavior while making arguments with GenAI, we created an online forum for soccer fans to engage in turn-based and free debates in a post format with the assistance of ChatGPT, arguing on the topic of "Messi vs Ronaldo". After 13 sessions of two-part study and semi-structured interviews with 39 participants, we conducted content and thematic analyses to integrate insights …

Meta-Clustering For Specialized Language Models: Enhancing Contextual Adaptation And Mitigating Hallucinations In Diverse Healthcare Environments, Joshit Mohanty, Vaishali Vaishali, Sandeep Kumar Nayak, Sumit Lahiri

Graduate Student Government Association Research Conference

Large Language Models (LLMs) have significantly advanced conversational AI by enabling dialogic information-seeking and task execution across diverse domains. However, their extensive parameters and broad domain scope lead to “data hallucinations.” These shortcomings are particularly evident in dynamic and diverse environments like India’s healthcare sector, where myriad languages, regional practices, and cultural nuances demand specialized, localized expertise rather than one-size-fits-all generalist models. This paper introduces a meta-clustering framework that integrates Distilled Language Models (DLMs) and Small/Specialized Language Models (SLMs) with meta-learning principles to address these limitations. By drawing on evidence from works such as MedHalu and Med-HALT, the framework seeks …

Ceker: A Generalizable Llm Framework For Literature Analysis With A Case Study In Unikernel Security, Alex Wollman, John Hastings

Research & Publications

Literature reviews are a critical component of formulating and justifying new research, but are a manual and often time-consuming process. This research introduces a novel, generalizable approach to literature analysis called CEKER which uses a three-step process to streamline the collection of literature, the extraction of key insights, and the summarized analysis of key trends and gaps. Leveraging Large Language Models (LLMs), this methodology represents a significant shift from traditional manual literature reviews, offering a scalable, flexible, and repeatable approach that can be applied across diverse research domains. A case study on unikernel security illustrates CEKER's ability to generate novel …

Bootstrapping Language Models With Dpo Implicit Rewards, Changyu Chen, Zichen Liu, Chao Du, Tianyu Pang, Qian Liu, Arunesh Sinha, Pradeep Varakantham, Min Lin

Research Collection School Of Computing and Information Systems

Human alignment in large language models (LLMs) is an active area of research. A recent groundbreaking work, direct preference optimization (DPO), has greatly simplified the process from past work in reinforcement learning from human feedback (RLHF) by bypassing the reward learning stage in RLHF. DPO, after training, provides an implicit reward model. In this work, we make a novel observation that this implicit reward model can by itself be used in a bootstrapping fashion to further align the LLM. Our approach is to use the rewards from a current LLM model to construct a preference dataset, which is then used …

Multimodal Ai-Driven Biomarker For Early Detection Of Cancer Cachexia, Sabeen Ahmed

USF Tampa Graduate Theses and Dissertations

Cancer cachexia is a metabolic syndrome characterized by substantial skeletal muscle loss, impacting cancer patients' survival and quality of life. Despite its clinical significance, early detection remains a challenge due to the lack of standardized diagnostic criteria and the reliance on indirect markers. This work presents an AI-driven approach to enhance cachexia detection and monitoring by integrating multiple deep learning methodologies. We explore transformer architectures for time-series analysis to model sequential medical data, enabling disease prediction and progression modeling. To ensure robust and reliable decision-making in clinical settings, we explore Bayesian deep neural networks for uncertainty estimation. Additionally, we introduce …

Investigating Key Structures In Protective Scenes For Llms, Eben M. Weisman

University Honors Theses

This research delves into the realm of "protective scenes" within Large Language Models (LLMs), exploring their impact on bias mitigation, deception, and context preservation. The study investigates the use of roleplay prompting human-like behavior and reasoning in LLMs, focusing on the Character-LLM framework's concept of protective scenes with graduated levels of protection. By combining insights from psychology, cognitive science, and computational analysis, this research aims to develop a framework for understanding how protective scenes influence roleplay performance in LLMs, ultimately contributing to the development of more reliable and ethical AI systems.

Examining Intersectional Queer Biases In Large Language Models: A Combined Statistical And Visual-Qualitative Approach For Quantification And Explanation, Huu Duong (Chip) Nguyen

Computer Science Senior Theses

Despite significant advancements in research on (intersectional) social biases in Large Language Models (LLMs), intersectional biases affecting subgroups within the LGBTQ+ community remain critically understudied. Existing bias detection methodologies often prioritize quantification but lack depth in explaining the specific stereotypes/biases that shape evaluation metrics. To address these gaps, this study proposes a combined statistical and visual-qualitative approach to quantify and identify persistent intersectional queer biases in five recent, state-of-the-art LLMs through a downstream story generation task. Findings from analysis uncover substantial evidence of stereotypes that perpetuate harmful, reductive narratives against intersectionally marginalized groups within the LGBTQ+ community. To promote public …

Attackg+: Boosting Attack Graph Construction With Large Language Models, Yongheng Zhang, Tingwen Du, Yunshan Ma, Xiang Wang, Yi Xie, Guozheng Yang, Yuliang Lu, Ee‑Chien Chang

Research Collection School Of Computing and Information Systems

Attack graph construction seeks to convert textual cyber threat intelligence (CTI) reports into structuredrepresentations, portraying the evolutionary traces of cyber attacks. Even though previous research hasproposed various methods to construct attack graphs, they generally suffer from limited generalizationcapability to diverse knowledge types as well as requirement of expertise in model design and tuning.Addressing these limitations, we seek to utilize Large Language Models (LLMs), which have achieved enormoussuccess in a broad range of tasks given exceptional capabilities in both language understanding and zeroshot task fulfillment. Thus, we propose a fully automatic LLM-based framework to construct attack graphsnamed: AttacKG+. Our framework consists …

Revisiting Sentiment Analysis For Software Engineering In The Era Of Large Language Models, Ting Zhang, Ivana Clairine Irsan, Thung Ferdian, David Lo

Research Collection School Of Computing and Information Systems

Software development involves collaborative interactions where stakeholders express opinions across various platforms. Recognizing the sentiments conveyed in these interactions is crucial for the effective development and ongoing maintenance of software systems. For software products, analyzing the sentiment of user feedback, e.g., reviews, comments, and forum posts can provide valuable insights into user satisfaction and areas for improvement. This can guide the development of future updates and features. However, accurately identifying sentiments in software engineering datasets remains challenging.This study investigates bigger large language models (bLLMs) in addressing the labeled data shortage that hampers fine-tuned smaller large language models (sLLMs) in software …

Evaluating Software Development Agents: Patch Patterns, Code Quality, And Issue Complexity In Real-World Github Scenarios, Zhi Chen, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

In recent years, AI-based software engineering has progressed from pre-trained models to advanced agentic workflows, with Software Development Agents representing the next major leap. These agents, capable of reasoning, planning, and interacting with external environments, offer promising solutions to complex software engineering tasks. However, while much research has evaluated code generated by large language models (LLMs), comprehensive studies on agent-generated patches, particularly in real-world settings, are lacking. This study addresses that gap by evaluating 4,892 patches from 10 top-ranked agents on 500 real-world GitHub issues from SWE-Bench Verified, focusing on their impact on code quality. Our analysis shows no single …

Yinyang-Align: Benchmarking Contradictory Objectives And Proposing Multi-Objective Optimization Based Dpo For Text-To-Image Alignment, Amitava Das, Yaswanth Narsupalli, Gurpreet Singh, Vinija Jain, Vasu Sharma, Suranjana Trivedi, Aman Chadha, Amit Sheth

Publications

As Text-to-Image (T2I) models become more advanced, they face a fundamental challenge—balancing conflicting alignment goals such as faithfulness vs. artistic freedom, realism vs. stylization, and verifiability vs. creativity. Existing alignment methods often optimize for one objective at the cost of another, leading to inconsistencies in AI-generated images.
/="/">
/="/">In our latest work, YinYang-Align, we introduce a benchmarking framework to systematically evaluate these trade-offs and propose Contradictory Alignment Optimization (CAO)—a multi-objective extension of Direct Preference Optimization (DPO) that enables models to navigate competing alignment goals more effectively.

A Deep Reinforcement Learning Framework For Sequential Art Creation, Asmin Pothula

Computer Science and Engineering Theses - Archive

Most computational art systems rely on generative models that produce a complete artwork in a single pass, without capturing the gradual, decision-driven process through which human artists construct visual pieces. Prior research in sequential, stroke-based image generation, including differentiable neural painters and model-based reinforcement learning agents, has explored step-by-step creation, but these systems typically aim to reconstruct the input image within the same visual representation space, closely matching brushstrokes, textures, or colors to the target. In contrast, this thesis investigates sequential art creation in a different artistic representation, where the final artwork does not share the same visual form as …

Leveraging Distributed Semantics From Deep Learning Architectures For Literature-Based Discovery, Clint A. Cuffy

Theses and Dissertations

Literature-based discovery (LBD) is a scientific process that introduces methods to automatically identify novel insights between non-interacting sets of literature. To date, numerous statistical and machine learning-based methods have been applied in the biomedical domain to find treatments for diseases such as Raynaud's disease, Parkinson's disease, and Multiple Sclerosis. However, the lack of standardized practices and creation of bespoke methodologies produces a scenario where the adoption of LBD remains challenging in real-world systems. Our work addresses these concerns through the improvement of five critical areas: 1) error propagation within LBD's a priori dependent tasks, 2) exploring the integration of modern …

Application Of Machine Learning And Large Language Models In Healthcare For Data Prediction And Summarization, Chiazam Chisom Izuchukwu

College of Graduate Studies: Theses & Dissertations

This study aims to examine the use of machine learning (ML) and large language models (LLMs) in healthcare to enhance disease prediction, clinical decision-making, and information management. Five supervised ML models—Logistic Regression (LR), Support Vector Machine (SVM), Random Forest (RF), Decision Trees (DT), and Naïve Bayes (NB)—on three different computing platforms—Google Colab, Databricks, and Snowflake—were employed for disease classification. Data preprocessing included treating missing values, encoding categorical variables utilizing one-hot-encoding, feature scaling when needed, and tackling class imbalance with Synthetic Minority Over-sampling Technique (SMOTE) before an 80-20 train-test separation. Models were created with Scikit-learn (Google Collab), Spark MLlib (Databricks), and …

Argue With Your Ai: Critically Engaging With Copilot, James Day

Publications

By now, you probably have some experience interacting with an AI chatbot. You might even have taken some training courses to learn about “prompt engineering” methods such as CO-STAR (Context, Objective, Style, Tone, Audience, Response)1 and RICCE (Relevance, Intent, Context, Clarity, Examples).2 In taking advantage of generative artificial intelligence, the focus is generally on writing that initial query. For this paper, let’s ignore advanced prompts asking for a complex analysis and consider the case where you’re simply looking for factual information.

Do Specialized Medical Llms Demand A Radically New Approach Under The Eu's Medical Device Regulation, Hannah Louise Smith, W. Nicholson Price Ii

Articles

We examine the arguments made by Onitiu and colleagues concerning the need to adopt a “backward-walking logic” to manage the risks arising from the use of Large Language Models (LLMs) adapted for a medical purpose. We examine what lessons can be learned from existing multi-use technologies and applied to specialized LLMs, notwithstanding their novelty, and explore the appropriate respective roles of device providers and regulators within the ecosystem of technological oversight.

Genai’S Impact On Global It Management: A Multi-Expert Perspective And Research Agenda, Yogesh K. Dwivedi, Laurie Hughes, Mohammad S. Al-Ahmadi, Vincent Dutot, Syed Q. Ahmed, Shahriar Akter, Rahul De’, Keyao Li, Nitish Singh, Paul Walton

Research outputs 2022 to 2026

Generative AI (GenAI) is disrupting global IT management and challenging established practice. The increasing use of GenAI technology is redefining localization, transforming existing workforce roles, outsourcing strategy, and team dynamics. Simultaneously, GenAI’s security complexities have prompted the rethinking of existing risk frameworks to meet a new set of challenges from GenAI enhanced cyber threats. This article explores these complex and converging factors, providing a roadmap to address GenAI’s significant impact on global IT management. We advocate the responsible adoption of GenAI and importance of building resilient, value-driven, globally consistent IT ecosystems able to adapt to the significant challenges and opportunities …

Heuristic Approaches For Coordination Of Heterogeneous Robotic Systems In Harvesting Automation With Size Constraints, Hyeseon Lee

Dissertations, Master's Theses and Master's Reports

This thesis presents the development of path planning algorithms for the coordination of heterogeneous robotic systems while considering size constraints. The objective is to generate practical and efficient solutions for real-world applications. The use of heterogeneous collaborative robots is beneficial in many applications, such as transportation operations in warehouses or manufacturing environments, surveillance, and monitoring, and task allocation and path planning are critical techniques that need to be addressed to deploy in real-world applications. This research focuses on automating lavender harvesting, where robots with varying capabilities must collaboratively navigate complex field layouts to efficiently complete harvesting tasks.

The problem considers …

Transforming Urban Dynamics: Harnessing Large Language Models For Smarter Mobility, Hao Xue, Ming Jin, Shirui Pan, Flora Salim, Guansong Pang

Research Collection School Of Computing and Information Systems

Artificial intelligence (AI) has the potential to analyze mobility data and make mobility systems smarter by leveraging diverse data sources such as geospatial data, transportation logs, and real-time sensor data to optimize traffic flow, enhance public transportation systems, and support the development of autonomous vehicles. With the newly emerged generative AI paradigm, exemplified by large language models (LLMs), there is great potential to transform the current AI applications in mobility, transportation, and urban domains. This article provides an overview of recent efforts and aims to shed light on the challenges and future opportunities to facilitate the adaptation of LLMs for …

Pixel: Ai Chatbot For Clear And Effective Senior Design Assistance, Asmin Pothula

2024 Fall Honors Capstone Projects - Archive

This research explores the development of an AI-driven chatbot named Pixel, specifically designed to assist Computer Science and Engineering Senior Design students by providing immediate, clear, and accurate responses to project-related queries. While my Senior Design project focuses on developing a "Senior Design Project Management Tool," my honors capstone project centers on developing Pixel and integrating it into both the project management tool and the CSE Senior Design Knowledge Base. Pixel leverages this knowledge base to offer guidance on tasks such as using lab equipment, performing technical procedures, and troubleshooting common issues, ensuring that students have swift access to relevant …

Enhancing Low-Resource Language Performance In Multilingual Large Language Models, Mingqi Li

All Dissertations

The large language models play an important role in many natural language tasks. However, training these models requires large amounts of data, which is not available for many languages. A noticeable performance gap exists between English and other languages, with low-resource languages showcasing this gap prominently. Therefore, it becomes imperative to improve large language models for low-resource languages. To address these challenges, we developed knowledge distillation and strategic prompt-learning, and attention alignment methods to improve the representation capabilities of large language models for low-resource language, and then enhanced their performance in downstream tasks.

In our first study, we developed a …

Automating Maritime Risk Data Collection And Identification Leveraging Large Language Models, Donghao Huang, Xiuju Fu, Xiaofeng Yin, Haibo Pen, Zhaoxia Wang

Research Collection School Of Computing and Information Systems

Maritime risk research is crucial yet challenging for improving safety, efficiency, and sustainability in maritime operations. This paper presents an innovative method for automating the collection and identification of risk data related to global maritime risks from news sources, addressing the limitations of traditional manual methods. To evaluate the proposed method, different learning-based models, including conventional machine learning approaches and advanced Large Language Models (LLMs) such as GPT-4 and LLaMA-3.1, are comprehensively studied for comparison. In addition, not only do we use popular evaluation metrics to assess the proposed method, but we also introduce a new evaluation metric, called the …

Thoughts To Target: Enhance Planning For Target-Driven Conversation, Zhonghua Zheng, Lizi Liao, Yang Deng, Ee-Peng Lim, Minlie Huang, Liqiang Nie

Research Collection School Of Computing and Information Systems

In conversational AI, large-scale models excel in various tasks but struggle with target-driven conversation planning. Current methods, such as chain-of-thought reasoning and tree-search policy learning techniques, either neglect plan rationality or require extensive human simulation procedures. Addressing this, we propose a novel two-stage framework, named EnPL, to improve the LLMs’ capability in planning conversations towards designated targets, including (1) distilling natural language plans from target-driven conversation corpus and (2) generating new plans with demonstration-guided in-context learning. Specifically, we first propose a filter approach to distill a high-quality plan dataset, ConvPlan1. With the aid of corresponding conversational data and support from …

Don’T Just Say “I Don’T Know”! Self-Aligning Large Language Models For Responding To Unknown Questions With Explanations, Yang Deng, Yong Zhao, Moxin Li, See-Kiong Ng, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Despite the remarkable abilities of Large Language Models (LLMs) to answer questions, they often display a considerable level of overconfidence even when the question does not have a definitive answer. To avoid providing hallucinated answers to these unknown questions, existing studies typically investigate approaches to refusing to answer these questions. In this work, we propose a novel and scalable self-alignment method to utilize the LLM itself to enhance its response-ability to different types of unknown questions, being capable of not only refusing to answer but also providing explanation to the unanswerability of unknown questions. Specifically, the Self-Align method first employ …

Experience As Source For Anticipation And Planning : Experiential Policy Learning For Target-Driven Recommendation Dialogues, Quang Huy Dao, Yang Deng, Khanh-Huyen Bui, Dung D. Le, Lizi Liao

Research Collection School Of Computing and Information Systems

Target-driven recommendation dialogues present unique challenges in dialogue management due to the necessity of anticipating user interactions for successful conversations. Current methods face significant limitations: (I) inadequate capabilities for conversation anticipation, (II) computational inefficiencies due to costly simulations, and (III) neglect of valuable past dialogue experiences. To address these limitations, we propose a new framework, Experiential Policy Learning (EPL), for enhancing such dialogues. EPL embodies the principle of Learning From Experience, facilitating anticipation with an experiential scoring function that estimates dialogue state potential using similar past interactions stored in long-term memory. To demonstrate its flexibility, we introduce Tree-structured EPL (T-EPL) …

A Survey Of Ontology Expansion For Conversational Understanding, Jinggui Liang, Yuxia Wu, Yuan Fang, Hao Fei, Lizi Liao

Research Collection School Of Computing and Information Systems

In the rapidly evolving field of conversational AI, Ontology Expansion (OnExp) is crucial for enhancing the adaptability and robustness of conversational agents. Traditional models rely on static, predefined ontologies, limiting their ability to handle new and unforeseen user needs. This survey paper provides a comprehensive review of the state-of-the-art techniques in OnExp for conversational understanding. It categorizes the existing literature into three main areas: (1) New Intent Discovery, (2) New Slot-Value Discovery, and (3) Joint OnExp. By examining the methodologies, benchmarks, and challenges associated with these areas, we highlight several emerging frontiers in OnExp to improve agent performance in real-world …

Collaborative Cross-Modal Fusion With Large Language Model For Recommendation, Zhongzhou Liu, Hao Zhang, Kuicai Dong, Yuan Fang

Research Collection School Of Computing and Information Systems

Despite the success of conventional collaborative filtering (CF) approaches for recommendation systems, they exhibit limitations in leveraging semantic knowledge within the textual attributes of users and items. Recent focus on the application of large language models for recommendation (LLM4Rec) has highlighted their capability for effective semantic knowledge capture. However, these methods often overlook the collaborative signals in user behaviors. Some simply instruct-tune a language model, while others directly inject the embeddings of a CF-based model, lacking a synergistic fusion of different modalities. To address these issues, we propose a framework of Collaborative Cross-modal Fusion with Large Language Models, termed CCF-LLM, …

Quality Assurance In Software Engineering: A Journey Towards Explainable Automated Solutions, Ratnadira Widyasari

Dissertations and Theses Collection (Open Access)

In today's digital era, the pervasive influence of software on daily life underscores the necessity for high-quality and reliable systems. Software failures can result in substantial harm and financial losses, highlighting the pivotal role of Software Quality Assurance (SQA). While automated SQA techniques have evolved to aid developers in ensuring software quality, the necessity for explainability in these automated solutions has become equally important. For example, in automated fault localization, only identifying suspicious locations is insufficient; it is essential to provide reasoning on why these locations are suspicious. This dissertation presents a series of interconnected studies aimed at developing explainable …