EC-OECD STIP Compass enhancement using Large Language Models

This project explores the integration of Large Language Models (LLMs) into the EC-OECD STIP Compass, aiming to enhance the efficiency and accuracy of science, technology, and innovation (STI) policy data collection. By leveraging AI, we tested the potential for LLMs to extract relevant policy information across six OECD countries, comparing AI-driven data with human-provided survey responses. The findings showcase the promise of AI-assisted survey methodologies and highlight opportunities for improving policy data analysis. This work represents a step towards a more dynamic, comprehensive approach to STI policy information, bridging human expertise with AI capabilities for more effective policymaking.