Positioning Political Texts with Large Language Models by Asking and Averaging

TL;DR

This paper demonstrates that instruction-tuned large language models can accurately and efficiently position political texts and actors within policy and ideological spaces by asking and averaging their responses, outperforming traditional supervised classifiers.

Contribution

It introduces a novel method of using instruction-tuned LLMs for positioning political texts, showing high correlation with expert and voting-based benchmarks across multiple languages.

Findings

High correlation (>0.90) with expert and voting benchmarks.

More accurate and cost-efficient than supervised classifiers.

Applicable across different languages and text lengths.

Abstract

We use instruction-tuned Large Language Models (LLMs) like GPT-4, Llama 3, MiXtral, or Aya to position political texts within policy and ideological spaces. We ask an LLM where a tweet or a sentence of a political text stands on the focal dimension and take the average of the LLM responses to position political actors such as US Senators, or longer texts such as UK party manifestos or EU policy speeches given in 10 different languages. The correlations between the position estimates obtained with the best LLMs and benchmarks based on text coding by experts, crowdworkers, or roll call votes exceed .90. This approach is generally more accurate than the positions obtained with supervised classifiers trained on large amounts of research data. Using instruction-tuned LLMs to position texts in policy and ideological spaces is fast, cost-efficient, reliable, and reproducible (in the case of open LLMs) even if the texts are short and written in different languages. We conclude with cautionary notes about the need for empirical validation.