English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Existing approaches to estimating politicians' latent positions alongspecific dimensions often fail when relevant data is limited. We leverage theembedded knowledge in generative large language models (LLMs) to address thischallenge and measure lawmakers' positions along specific political or policydimensions. We prompt an instruction/dialogue-tuned LLM to pairwise comparelawmakers and then scale the resulting graph using the Bradley-Terry model. Weestimate novel measures of U.S. senators' positions on liberal-conservativeideology, gun control, and abortion. Our liberal-conservative scale, used tovalidate LLM-driven scaling, strongly correlates with existing measures andoffsets interpretive gaps, suggesting LLMs synthesize relevant data frominternet and digitized media rather than memorizing existing measures. Our guncontrol and abortion measures -- the first of their kind -- differ from theliberal-conservative scale in face-valid ways and predict interest groupratings and legislator votes better than ideology alone. Our findings suggestLLMs hold promise for solving complex social science measurement problems.

Large Language Models Can Be Used to Estimate the Latent Positions of Politicians