Can Large Language Models Transform Computational Social Science?

arXiv:2305.03514v3 Announce Type: replace-cross
Abstract: Large Language Models (LLMs) are capable of successfully performing many language processing tasks zero-shot (without training data). If zero-shot LLMs can also reliably classify and explain social phenomena like persuasiveness and political ideology, then LLMs could augment the Computational Social Science (CSS) pipeline in important ways. This work provides a road map for using LLMs as CSS tools. Towards this end, we contribute a set of prompting best practices and an extensive evaluation pipeline to …

abstract arxiv computational cs.cl cs.lg css data language language models language processing large language large language models llms pipeline political processing science social social science tasks training training data type zero-shot