Positioning Political Texts with Large Language Models by Asking and Averaging
The DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.
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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Applying LLMs to tasks from Benoit et al. (2016), both Le Mens and Gallego and Ornstein et al. used LLMs to replicate crowd-sourced and expert classifications of policy content at the sentence level (Le Mens & Gallego, 2025;Ornstein et al., 2025).”
From Using large language models to analyze political texts through natural language understanding (2026) · cites this paper as Le Mens & Gallego, 2025
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
Extracting Policy Positions from Political Texts Using Words as Data
LAVER, M., BENOIT, K., & GARRY, J. (2003) · American Political Science Review · doi:10.1017/s0003055403000698 · Cited by 1,377 · cited 1×
“Widely used approaches involve the automatic processing of text documents produced by these actors, such as party manifestos (Laver et al., 2003; Slapin and Proksch, 2008) or legislative speeches (Lauderdale and Herzog, 2016).”
Birds of the Same Feather Tweet Together: Bayesian Ideal Point Estimation Using Twitter Data
Barberá, P. (2015) · Political Analysis · doi:10.1093/pan/mpu011 · Cited by 1,298 · cited 1×
“Yet other approaches rely on other inputs, such as roll call votes (Poole and Rosenthal, 1985), Twitter connections (Barberá, 2015), or campaign donations (Bonica, 2014).”
BackgroundChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks
Gilardi, F., Alizadeh, M., & Kubli, M. (2023) · arXiv · doi:10.48550/arxiv.2303.15056 · Cited by 1,207
ChatGPT outperforms crowd workers for text-annotation tasks
Gilardi, F., Alizadeh, M., & Kubli, M. (2023) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2305016120 · Cited by 1,197 · cited 1×
“…have shown that LLMs can produce text annotations (classifications in discrete categories such as relevant/irrelevant or a topic among a limited set of candidate topics) that are in good agreement with those produced by human coders (e.g., Gilardi et al., 2023; Törnberg, 2023; Ziems et al., 2023).”
Birds of the Same Feather Tweet Together. Bayesian Ideal Point Estimation Using Twitter Data
Barbera, P. (2012) · doi:10.2139/ssrn.2108098 · Cited by 983
Can Large Language Models Transform Computational Social Science?
Ziems, C., Held, W., Shaikh, O., Chen, J., Zhang, Z., & Yang, D. (2023) · arXiv · doi:10.48550/arxiv.2305.03514 · Cited by 839
A Scaling Model for Estimating Time‐Series Party Positions from Texts
Slapin, J. B., & Proksch, S. (2008) · American Journal of Political Science · doi:10.1111/j.1540-5907.2008.00338.x · Cited by 684
Mapping the Ideological Marketplace
Bonica, A. (2014) · American Journal of Political Science · doi:10.1111/ajps.12062 · Cited by 680
Can Large Language Models Transform Computational Social Science?
Ziems, C., Held, W., Shaikh, O., Chen, J., Zhang, Z., & Yang, D. (2024) · Computational Linguistics · doi:10.1162/coli_a_00502 · Cited by 585
Research works printed but not linked: 10
- 10.1093/oso/9780199244003.001.0001 · DOI · Paper page
- 10.1093/pan/mpw017 · DOI · Paper page
- 10.15195/v10.a3 · DOI
- 10.1017/S0003055416000058 · DOI · Paper page
- 10.4135/9781526486387.n29 · DOI · Paper page
- 10.3162/036298004X201294 · DOI · Paper page
- 10.1073/pnas.2309350120 · DOI
- 10.2307/2111172 · DOI · Paper page
- 10.1177/08944393241286 · doi:10.1177/08944393241286
- 10.1017/psrm.2024.64 · DOI · Paper page
Cited by
Using large language models to analyze political texts through natural language understanding
Benoit, K., De Marchi, S., Laver, C., Laver, M., & Ma, J. (2026) · American Journal of Political Science · doi:10.1111/ajps.70050 · Cited by 37
Metadata
- Authors
- Le Mens, G., & Gallego, A.
- Venue
- Political Analysis
- Publisher
- Cambridge University Press (CUP)
- Published
- 2025-01-27
- Volume
- 33
- Issue
- 3
- Pages
- 274-282
- ISSN
- 1047-1987
- 1476-4989
- Cited by
- 42
- References
- 11
- Language
- en
- Funders
- Directorate-General XII, Science, Research, and Development (ERC Consolidator Grant 772268)
- Ministerio de Ciencia y Tecnología (PID2019-105249GBI00)
- Ministerio de Ciencia, Innovación y Universidades (PID2021-123111OB-I00)
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.