Large Language Models Can Be Used to Estimate the Latent Positions of Politicians
By Patrick Y. Wu, Joshua A. Tucker, Jonathan Nagler, Solomon Messing. 2023
41 citations recorded by the source corpus.
Existing approaches to estimating politicians' latent positions along specific dimensions often fail when relevant data is limited. We leverage the embedded knowledge in generative large language models (LLMs) to address this challenge and measure lawmakers' positions along specific political or policy dimensions. We prompt an instruction/dialogue-tuned LLM to pairwise compare lawmakers and then scale the resulting graph using the Bradley-Terry model. We estimate novel measures of U.S. senators' positions on liberal-conservative ideology, gun control, and abortion. Our liberal-conservative scale, used to validate LLM-driven scaling, strongly correlates with existing measures and offsets interpretive gaps, suggesting LLMs synthesize relevant data from internet and digitized media rather than memorizing existing measures. Our gun control and abortion measures -- the first of their kind -- differ from the liberal-conservative scale in face-valid ways and predict interest group ratings and legislator votes better than ideology alone. Our findings suggest LLMs hold promise for solving complex social science measurement problems.
Subfields: General Social Sciences, Political Science and International Relations, Sociology and Political Science, Large Language Models
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Political Science and International Relations
In Sociology and Political Science
- Fabrizio Gilardi
- Martino Maggetti
- Hung-yi Lee
- Cheng-Han Chiang
- Christel Koop
- Chris Hanretty
- M. Lodge
Citations in the corpus
- ChatGPT outperforms crowd workers for text-annotation tasks (2023, background): “LLMs have been shown to perform very well for a wide range of purposes, including ideological scaling (Wu et al., 2023), the classification of legislative proposals (Nay, 2023), the resolution of cognitive psychology tasks, (Binz and Schulz, 2023), and the simulation of human samples for survey…”