mlsanityData to 14 Oct 2026

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

arXiv 2303.12057 ↗First posted 21 Mar 2023cs.CY cs.CLcited by 33

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 33 papers in the map (data through 14 Oct 2026). Builds on 6 of its 53 references that are in the map. First posted on arXiv 21 Mar 2023.

Builds on

6 of 53 references.

References · 6

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2022Training language models to follow instructions with human feedbackcited by 15,971
  4. 2017Proximal Policy Optimization Algorithmscited by 15,215
  5. 2019Fine-Tuning Language Models from Human Preferencescited by 2,150
  6. 2022Out of One, Many: Using Language Models to Simulate Human Samplescited by 752

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 6; 2024: 11; 2025: 8; 2026: 8.

33 papers.

Sort:

By area:

  1. 2023ChatGPT Outperforms Crowd-Workers for Text-Annotation Taskscited by 870
  2. 2024Random Silicon Sampling: Simulating Human Sub-Population Opinion Using a Large Language Model Based on Group-Level Demographic Informationcited by 49
  3. 2023Using Imperfect Surrogates for Downstream Inference: Design-based Supervised Learning for Social Science Applications of Large Language Modelscited by 39
  4. 2025Linear Representations of Political Perspective Emerge in Large Language Modelscited by 32
  5. 2025The simulation of judgment in LLMscited by 22
  6. 2024The Potential and Challenges of Evaluating Attitudes, Opinions, and Values in Large Language Modelscited by 19
  7. 2023Positioning Political Texts with Large Language Models by Asking and Averagingcited by 13
  8. 2024Language Models can Subtly Deceive Without Lying: A Case Study on Strategic Phrasing in Legislationcited by 10
  9. 2024A Large-Scale Simulation on Large Language Models for Decision-Making in Political Sciencecited by 10
  10. 2024Latent State Estimation Helps UI Agents to Reasoncited by 9
  11. 2024LLMs left, right, and center: Assessing GPT's capabilities to label political bias from web domainscited by 9
  12. 2023How to use LLMs for Text Analysiscited by 5
21 more
  1. 2023Concept-Guided Chain-of-Thought Prompting for Pairwise Comparison Scoring of Texts with Large Language Modelscited by 5
  2. 2024LLMs May Not Be Human-Level Players, But They Can Be Testers: Measuring Game Difficulty with LLM Agentscited by 5
  3. 2025Synthesizing Public Opinions with LLMs: Role Creation, Impacts, and the Future to eDemorcacycited by 5
  4. 2024Adaptive Uncertainty Quantification for Generative AIcited by 4
  5. 2024LLM-POTUS Score: A Framework of Analyzing Presidential Debates with Large Language Modelscited by 2
  6. 2023Multiclass Classification of Policy Documents with Large Language Modelscited by 1
  7. 2024L(u)PIN: LLM-based Political Ideology Nowcastingcited by 1
  8. 2024Identifying the sources of ideological bias in GPT models through linguistic variation in outputcited by 1
  9. 2025Agent-Enhanced Large Language Models for Researching Political Institutionscited by 1
  10. 2025VisTopics: A Visual Semantic Unsupervised Approach to Topic Modeling of Video and Image Datacited by 1
  11. 2026Validating Political Position Predictions of Argumentscited by 1
  12. 2026Item-Mean Surrogates: Why Richer Persona Data Fail to Improve LLMs as Human Surrogatescited by 1
  13. 2025Efficient Portfolio Selection through Preference Aggregation with Quicksort and the Bradley--Terry Modelcited by 0
  14. 2025Persona-driven Simulation of Voting Behavior in the European Parliament with Large Language Modelscited by 0
  15. 2025Shachi: A Modular, Controllable Framework for LLM-Based Agent-Based Modeling of Emergent Collective Behaviorcited by 0
  16. 2026Agentic Framework for Political Biography Extractioncited by 0
  17. 2026Does Topic Sentiment Cause Perceived Ideology? Comparing Human and LLM Annotations in Political News Articlescited by 0
  18. 2026The Model as One Rater Among Several: Measuring Political Positions in Data-Sparse Regions with a Language-Model Panelcited by 0
  19. 2026Validating LLMs in social science: Epistemic threats and emerging normscited by 0
  20. 2026Multi-dimensional Bias in Modeling Multi-dimensional Preferences: Evaluating the Ability of Synthetic Agents to Replace Human Participants in Conjoint Experimentscited by 0
  21. 2026Making Political Text Scaling Comparable: Infrastructure and Hyperparameter Sensitivity for 17 Algorithmscited by 0