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

arXiv cs.AI / 3/12/2026

💬 OpinionDeveloper Stack & InfrastructureModels & Research

共有:

Key Points

TAMUSA-Chat is a research-oriented framework designed to enable domain adaptation of large language model conversational systems for institutional contexts.
It combines supervised fine-tuning, retrieval-augmented generation, and systematic evaluation to address data acquisition, preprocessing, embedding construction, and training workflows.
The architecture supports modular components for reproducible experimentation with training configurations, hyper-parameters, and deployment strategies, emphasizing governance and responsible AI practices.
The work provides empirical analysis on fine-tuning across model sizes, discusses efficiency, compute-resource requirements, quality-cost trade-offs, and releases a public codebase for continued research.

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.