TAMUSA-Chat: A Domain-Adapted Large Language Model Conversational System for Research and Responsible Deployment

TL;DR

TAMUSA-Chat is a framework for creating domain-specific conversational AI systems tailored for research institutions, emphasizing transparency, governance, and responsible AI practices through systematic adaptation and evaluation.

Contribution

It introduces a comprehensive architecture and methodology for adapting large language models to institutional domains, including data processing, training, and deployment strategies.

Findings

Effective domain adaptation demonstrated across model sizes

Insights into training efficiency and quality-cost trade-offs

Open-source code supports further research and development

Abstract

This paper presents TAMUSA-Chat, a research-oriented framework for building domain-adapted large language model conversational systems. The work addresses critical challenges in adapting general-purpose foundation models to institutional contexts through supervised fine-tuning, retrieval-augmented generation, and systematic evaluation methodologies. We describe the complete architecture encompassing data acquisition from institutional sources, preprocessing pipelines, embedding construction, model training workflows, and deployment strategies. The system integrates modular components enabling reproducible experimentation with training configurations, hyper-parameters, and evaluation protocols. Our implementation demonstrates how academic institutions can develop contextually grounded conversational agents while maintaining transparency, governance compliance, and responsible AI practices. Through empirical analysis of fine-tuning behavior across model sizes and training iterations, we provide insights into domain adaptation efficiency, computational resource requirements, and quality-cost trade-offs. The publicly available codebase at https://github.com/alsmadi/TAMUSA_LLM_Based_Chat_app supports continued research into institutional LLM deployment, evaluation methodologies, and ethical considerations for educational AI systems.