Evidence-based policy or beauty contest? An LLM-based meta-analysis of EU cohesion policy evaluations

Independent and high-quality evaluations of government policies are an important input for designing evidence-based policy. Lack of incentives and institutions to write such evaluations, on the other hand, carry the risk of turning the system into a costly beauty contest. We study one of the most advanced markets of policy evaluations in the world, the evaluations of EU Cohesion Policies by its Member States (MS). We use large language models quantify the findings of about 2,300 evaluations, and complement this data with our own survey of the authors. We show that the findings of evaluations are inconsistent with those of the academic literature on the output impacts of Cohesion Policy. Using further variation across MS, our analysis suggests that the market of evaluations is rather oligopolistic within MS, that it is very fragmented across the EU, and that there is often a strong involvement of managing authorities in the work of formally independent evaluators. These factors contribute to making the findings of the evaluations overly optimistic (beautiful) risking their overall usefulness (evidence-based policy). We conclude by discussing reform options to make the evaluations of EU Cohesion Policies more unbiased and effective.