.png){kind=icon}
返回
Can Large Language Models Transform Computational Social Science?
.png){kind=icon}
OA
AI
DOI：10.1162/coli_a_00502.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
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 measure the zero-shot performance of 13 language models on 25 representative English CSS benchmarks. On taxonomic labeling tasks (classification), LLMs fail to outperform the best fine-tuned models but still achieve fair levels of agreement with humans. On free-form coding tasks (generation), LLMs produce explanations that often exceed the quality of crowdworkers' gold references. We conclude that the performance of today's LLMs can augment the CSS research pipeline in two ways: (1) serving as zero-shot data annotators on human annotation teams, and (2) bootstrapping challenging creative generation tasks (e.g., explaining the underlying attributes of a text). In summary, LLMs are posed to meaningfully participate in social science analysis in partnership with humans.
Keyword:
STANCE DETECTION
PERSONALITY
CULTURE
EVENTS
MEDIA
PERSUASION
EXTRACTION
IDENTITY
DECISION
STYLES
期刊
IF:
5.3
论文数:
837
被引数:
2.7K
机构
引用论文
分享收藏Cellulitis: Home Or Inpatient in Children from the Emergency Department (CHOICE): protocol for a randomised controlled trial.png)
BMJ Open
OAAI
BMJ OpenIF0
OAAI分享收藏分享收藏分享收藏分享收藏
查看更多内容