Towards Trustworthy and Effective AI for Academic Policy Navigation: Human Evaluation of a Source-Aware, Domain-Optimized RAG-Based Chatbot

Towards Trustworthy and Effective AI for Academic Policy Navigation: Human Evaluation of a Source-Aware, Domain-Optimized RAG-Based Chatbot

Navigating institutional policies remains a challenge for students and staff due to complex legalistic language, hierarchical structures, and dispersed documentation. While Large Language Models (LLMs) such as GPT-4o offer fluent natural language capabilities, their susceptibility to hallucina...