A key policy question in evaluating social programs to address childhood poverty is how families receiving unconditional financial support would spend those funds. Economists have limited empirical evidence on this topic in the U.S. We provide causal estimates of financial and time investments...

How can we use the novel capacities of large language models (LLMs) in empirical research? And how can we do so while accounting for their limitations, which are themselves only poorly understood? We develop an econometric framework to answer this question that distinguishes between two types of...