Working Papers

This paper proposes the use of synthetic training data generated by large language models
to improve machine learning SDG classifiers. It shows that supplementing existing training data with
synthetic data produced by the ChatGPT tool improves the performance of the SDGClassy classifier.
This addition of synthetic data is especially useful in building SDG classifiers given the limited availability
of properly labeled data and the complex, interconnected nature of the SDGs. Synthetic data thus enables
more effective machine-learning applications in this context.

The Addis Ababa Action Agenda of the Third Conference on Financing for Development underscores sustainable and resilient infrastructure as a pre-requisite to sustainable development. Public-Private Partnerships (PPPs) are expected to deliver infrastructure in furtherance of this Agenda. In view of this expectation, twelve prominent PPP guidelines were reviewed for alignment with the Addis Agenda and key public governance factors. The research found that the PPP guidelines are not sufficiently aligned with the Addis Agenda, have insufficient sustainability content, and do not acknowledge the role of the public in PPPs. It recommends that the next generation of the guidelines address these…