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.

This paper discusses Uzbekistan’s recent experience with structural shifts and industrial policy and the larger implications for existing theories of industrial policy. The paper has a particular focus on various industry policy instruments.

Two major hypotheses are discussed: (1) the hypothesis of Haussmann, Hwang and Rodrik (the more technologically sophisticated the export structure, the better for growth) and (2) the hypothesis of Justin Yifu Lin (export specialization should build on existing comparative advantages and not jump over the necessary technological stages).