Skip to content
Open access

AI-Driven Project Management Knowledge Systems: Developing a Lora-Fine-Tuned Chatbot Using a Large-Scale Domain Dataset

Oct 2026 · Proceedings of the 30th International Congress on Project Management “Beyond Success: Happiness and Wellbeing in the Project Environment” · 0 citations

Abstract

Today’s project environments are at the intersection of information-intensive fields, including methodology management, risk analysis, resource planning, and cost control. Therefore, rapid and contextually sensitive access to accurate information is critical for professionals. The static structure of traditional information systems often fails to adequately support dynamic decision‑making processes and can lead to cognitive overload. In this study, an AI‑supported interactive knowledge assistant specifically designed for the field of project management was developed. Approximately 700 academic and professional sources were systematically analysed, and based on this foundation, 100,000 unique question–answer pairs were generated using the Qwen3‑Max model. The model was fine‑tuned using the Low‑Rank Adaptation (LoRA) method and demonstrated stable convergence within the Gemini training environment. The findings indicate that parameter‑efficient fine‑tuning with domain‑specific datasets significantly improves the contextual accuracy and practical value of large language models, suggesting that artificial intelligence can support not only project success but also the well‑being of professionals by reducing cognitive load.

Read PDF

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.