GenAI for Research Support: A Case to DMPs Pre-Filling
TL;DR
A GenAI tool was developed that used a Large Language Model capable of answering typical questions for a DMP after receiving the original research proposal as input, and showed a very good capability in providing appropriate responses to most of the DMP questions.
Abstract
Our aim with this report was to present the application of Generative AI (GenAI) in the preparation of Data Management Plans (DMPs), which are typically mandatory for funded research proposals. We developed a GenAI tool that used a Large Language Model (LLM) capable of answering typical questions for a DMP (e.g., What are the research questions? Are human participants involved?) after receiving the original research proposal as input. In our initial attempts, based on publicly available proposals from the Dutch Research Council and the European Research Council, the LLM showed a very good capability in providing appropriate responses to most of the DMP questions. We then organised a user testing session with researchers at Eindhoven University of Technology to validate our initial investigations. We discussed with them how effective they thought the LLM would be if used for their next DMP preparation, specifically in terms of time saved in preparing their plan, as well as what extra features they thought might better equip the LLM to help them in improving their Research Data Management workflow. Our work proved the effectiveness of this new technology, paving the way for future work that would enable GenAI to support researchers and data stewards in preparing, submitting and reviewing DMPs.
