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

arXiv: https://arxiv.org/abs/2303.12057 · HTML: https://mlsanity.com/paper/2303.12057/

## 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 (most cited first, 6 of 6)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Out of One, Many: Using Language Models to Simulate Human Samples](https://mlsanity.com/paper/2209.06899/) (2022)

## Built on by (most cited first, 30 of 33)

- [ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks](https://mlsanity.com/paper/2303.15056/) (2023)
- [Random Silicon Sampling: Simulating Human Sub-Population Opinion Using a Large Language Model Based on Group-Level Demographic Information](https://mlsanity.com/paper/2402.18144/) (2024)
- [Using Imperfect Surrogates for Downstream Inference: Design-based Supervised Learning for Social Science Applications of Large Language Models](https://mlsanity.com/paper/2306.04746/) (2023)
- [Linear Representations of Political Perspective Emerge in Large Language Models](https://mlsanity.com/paper/2503.02080/) (2025)
- [The simulation of judgment in LLMs](https://mlsanity.com/paper/2502.04426/) (2025)
- [The Potential and Challenges of Evaluating Attitudes, Opinions, and Values in Large Language Models](https://mlsanity.com/paper/2406.11096/) (2024)
- [Positioning Political Texts with Large Language Models by Asking and Averaging](https://mlsanity.com/paper/2311.16639/) (2023)
- [Language Models can Subtly Deceive Without Lying: A Case Study on Strategic Phrasing in Legislation](https://mlsanity.com/paper/2405.04325/) (2024)
- [A Large-Scale Simulation on Large Language Models for Decision-Making in Political Science](https://mlsanity.com/paper/2412.15291/) (2024)
- [Latent State Estimation Helps UI Agents to Reason](https://mlsanity.com/paper/2405.11120/) (2024)
- [LLMs left, right, and center: Assessing GPT's capabilities to label political bias from web domains](https://mlsanity.com/paper/2407.14344/) (2024)
- [How to use LLMs for Text Analysis](https://mlsanity.com/paper/2307.13106/) (2023)
- [Concept-Guided Chain-of-Thought Prompting for Pairwise Comparison Scoring of Texts with Large Language Models](https://mlsanity.com/paper/2310.12049/) (2023)
- [LLMs May Not Be Human-Level Players, But They Can Be Testers: Measuring Game Difficulty with LLM Agents](https://mlsanity.com/paper/2410.02829/) (2024)
- [Synthesizing Public Opinions with LLMs: Role Creation, Impacts, and the Future to eDemorcacy](https://mlsanity.com/paper/2504.00241/) (2025)
- [Adaptive Uncertainty Quantification for Generative AI](https://mlsanity.com/paper/2408.08990/) (2024)
- [LLM-POTUS Score: A Framework of Analyzing Presidential Debates with Large Language Models](https://mlsanity.com/paper/2409.08147/) (2024)
- [Multiclass Classification of Policy Documents with Large Language Models](https://mlsanity.com/paper/2310.08167/) (2023)
- [L(u)PIN: LLM-based Political Ideology Nowcasting](https://mlsanity.com/paper/2405.07320/) (2024)
- [Identifying the sources of ideological bias in GPT models through linguistic variation in output](https://mlsanity.com/paper/2409.06043/) (2024)
- [Agent-Enhanced Large Language Models for Researching Political Institutions](https://mlsanity.com/paper/2503.13524/) (2025)
- [VisTopics: A Visual Semantic Unsupervised Approach to Topic Modeling of Video and Image Data](https://mlsanity.com/paper/2505.14868/) (2025)
- [Validating Political Position Predictions of Arguments](https://mlsanity.com/paper/2602.18351/) (2026)
- [Item-Mean Surrogates: Why Richer Persona Data Fail to Improve LLMs as Human Surrogates](https://mlsanity.com/paper/2608.29455/) (2026)
- [Efficient Portfolio Selection through Preference Aggregation with Quicksort and the Bradley--Terry Model](https://mlsanity.com/paper/2504.16093/) (2025)
- [Persona-driven Simulation of Voting Behavior in the European Parliament with Large Language Models](https://mlsanity.com/paper/2506.11798/) (2025)
- [Shachi: A Modular, Controllable Framework for LLM-Based Agent-Based Modeling of Emergent Collective Behavior](https://mlsanity.com/paper/2509.21862/) (2025)
- [Agentic Framework for Political Biography Extraction](https://mlsanity.com/paper/2603.18010/) (2026)
- [Does Topic Sentiment Cause Perceived Ideology? Comparing Human and LLM Annotations in Political News Articles](https://mlsanity.com/paper/2606.06715/) (2026)
- [The Model as One Rater Among Several: Measuring Political Positions in Data-Sparse Regions with a Language-Model Panel](https://mlsanity.com/paper/2606.23042/) (2026)

## 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.