Large Language Models Can Be a Viable Substitute for Expert Political Surveys When a Shock Disrupts Traditional Measurement Approaches
Not on the map. Why?
Abstract (arXiv)
After a disruptive event or shock, such as the Department of Government Efficiency (DOGE) federal layoffs of 2025, expert judgments are colored by knowledge of the outcome. This can make it difficult or impossible to reconstruct the pre-event perceptions needed to study the factors associated with the event. This position paper argues that large language models (LLMs), trained on vast amounts of digital media data, can be a viable substitute for expert political surveys when a shock disrupts traditional measurement. We analyze the DOGE layoffs as a specific case study for this position. We use pairwise comparison prompts with LLMs and derive ideology scores for federal executive agencies. These scores replicate pre-layoff expert measures and predict which agencies were targeted by DOGE. We also use this same approach and find that the perceptions of certain federal agencies as knowledge institutions predict which agencies were targeted by DOGE, even when controlling for ideology. This case study demonstrates that using LLMs allows us to rapidly and easily test the associated factors hypothesized behind the shock. More broadly, our case study of this recent event exemplifies how LLMs offer insights into the correlational factors of the shock when traditional measurement techniques fail. We conclude by proposing a two-part criterion for when researchers can turn to LLMs as a substitute for expert political surveys.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 18 of its 68 references that are in the map. First posted on arXiv 6 Jun 2025.
Builds on
18 of 68 references.
References · 18
- 2023Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMscited by 974
- 2023Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formattingcited by 817
- 2022Out of One, Many: Using Language Models to Simulate Human Samplescited by 752
- 2022Teaching Models to Express Their Uncertainty in Wordscited by 751
- 2023Generating with Confidence: Uncertainty Quantification for Black-box Large Language Modelscited by 293
- 2023Can Large Language Models Transform Computational Social Science?cited by 250
- 2020Reducing conversational agents' overconfidence through linguistic calibrationcited by 210
- 2023Do LLMs exhibit human-like response biases? A case study in survey designcited by 180
- 2024Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Modelscited by 162
- 2024ProSA: Assessing and Understanding the Prompt Sensitivity of LLMscited by 149
- 2023Navigating the Grey Area: How Expressions of Uncertainty and Overconfidence Affect Language Modelscited by 91
- 2024Uncertainty Estimation and Quantification for LLMs: A Simple Supervised Approachcited by 76
6 more
- 2025Language Model Fine-Tuning on Scaled Survey Data for Predicting Distributions of Public Opinionscited by 66
- 2024Virtual Personas for Language Models via an Anthology of Backstoriescited by 51
- 2023Positioning Political Texts with Large Language Models by Asking and Averagingcited by 13
- 2023Measurement in the Age of LLMs: An Application to Ideological Scalingcited by 11
- 2023Crowdsourcing subjective annotations using pairwise comparisons reduces bias and error compared to the majority-vote methodcited by 10
- 2023Concept-Guided Chain-of-Thought Prompting for Pairwise Comparison Scoring of Texts with Large Language Modelscited by 5
Built on by
Citing papers per year: 2026: 1.
1 paper.