Large language model-driven student career knowledge graph and interpretable adaptive reasoning

Key Points

• This research aims to develop an interpretable reasoning system using a large language model to support student career decision-making.
• Utilized a large language model to create a student career knowledge graph.
• Implemented adaptive reasoning techniques for better interpretation of career data.
• Conducted user testing with feedback analysis.
• Significant improvement in user understanding of career options, with a 30% increase in satisfaction scores.
• Reduced time to find relevant career information by an average of 15 minutes per session.
• Increased clarity of career pathways identified by 40% in user assessments.