DBIS

This thesis aims to explore and prototype a system for participatory governance and transparent decision-making in the context of modernizing legacy software systems. Using Large Language Models (LLMs), the system will analyze and extract decisions from various project artifacts (e.g., commit messages, meeting transcripts), represent them in a structured decision domain model, and create an audit trail that supports stakeholder engagement, accountability, and traceability throughout the modernization process.

The overall goal is to support more inclusive, explainable, and well-documented modernization strategies by making both decisions and their rationales visible and verifiable to all relevant stakeholders.

With rapid advances in artificial intelligence, especially large language models (e.g., OpenAI GPT, Anthropic Claude, Google Gemini), AI has demonstrated great potential in natural language processing, code generation, and automated testing. Programming, traditionally a highly specialized and creative task, is increasingly supported and partially automated by AI. Tools such as GitHub Copilot and OpenAI Codex already generate code snippets based on natural language prompts, boosting developer productivity.

However, current AI code generation systems face challenges such as limited context understanding, inconsistent code quality, lack of adaptation to complex software engineering workflows, and limited capacity for continuous interaction and collaboration. Therefore, building an intelligent coding agent system capable of autonomous planning, requirement comprehension, code writing, debugging, and optimization has become a cutting-edge research topic in academia and industry.

As software engineering continues to evolve, agile frameworks have become the main paradigm for project management and development. Among these, Scrum is widely adopted by numerous software organizations due to its iterative and incremental development approach, emphasis on team collaboration, and rapid feedback cycles. With the ongoing advancements in artificial intelligence technologies, particularly the recent breakthroughs in large language models, there is growing interest in integrating AI throughout the entire lifecycle to improve efficiency and quality further.
 

While recent advancements in natural language processing have been largely driven by increasingly powerful large language models (LLMs), the role of data quality in fine-tuning these models remains underexplored. This thesis addresses the often-overlooked but critical aspect of data-centric AI by investigating how different types and levels of data degradation affect the performance of fine-tuned LLMs on tasks such as summarization and question answering. Unlike model-centric approaches that focus on architectural improvements, this work systematically introduces controlled degradations, such as spelling errors, grammatical mistakes, and semantic noise, into high-quality datasets. The goal is to quantify how these degradations impact downstream performance and identify which types of data noise are most detrimental. The results aim to inform best practices in dataset curation and reinforce the importance of data quality in building robust, task-specific LLM applications.