most citedUsing Imperfect Surrogates for Downstream Inference: Design-based Supervised Learning for Social Science Applications of Large Language Models

24 citations · 24 across the 1 of their papers we have counts for

collaborators

1 paper

stat.ME2023★ 24 cited

Using Imperfect Surrogates for Downstream Inference: Design-based Supervised Learning for Social Science Applications of Large Language Models

Naoki Egami, Musashi Hinck, Brandon M. Stewart +1

In computational social science (CSS), researchers analyze documents to explain social and political phenomena. In most scenarios, CSS researchers first obtain labels for documents…