The Model as One Rater Among Several: Measuring Political Positions in Data-Sparse Regions with a Language-Model Panel
Abstract
Most instruments for measuring political positions, such as manifesto coding, expert surveys and text-scaling models, were built and validated on Western party systems, and they break down worst where many consequential actors never publish a manifesto, never contest a competitive election, or commit one position to a charter and act on another in office. This paper proposes a method for such settings. I treat a large language model as a single fallible rater in a panel, the way an expert survey treats one expert, and describe the panel, its synthesis, an applicability rule that keeps a blank distinct from a zero, and a lens that separates what an actor declares from what it does. Three results follow. First, a built-in experiment isolates the rubric: with a definition-free round held fixed, written axis definitions move scores by a mean of 1.8 points on a 21-point scale and tighten agreement between raters (mean absolute gap 2.81 to 2.50; r 0.81 to 0.89). Second, across nine models from eight laboratories in two countries, Krippendorff's alpha is 0.86 on an interval and 0.87 on an ordinal metric, and it held as the panel grew from five raters to nine. This is reliability and says nothing yet about validity, since models trained on overlapping data can share a bias no statistic computed from the models can detect. Third, the panel's sharpest split, a bimodal divergence on an actor's stance toward the state's foundational order, comes from a referent problem: the models agree on the facts and differ on which order counts as the regime. A blind triple-coding traces about two-thirds of such disagreement to interpretation. The worked example is the Middle East and North Africa, and the rubric, prompt and data are released in full.
Related
- A Scalable Framework for Simultaneously Optimizing Damper Positions and Viscosities
- Counting Reachable Positions in a Simplified Model of Connect Four
- Addendum to: Mahler's method in several variables and finite automata
- Operator representations of Herglotz-Nevanlinna functions in several variables
- Tightness of and counterexamples to several quantum estimates
BibTeX
@misc{gara2026model,
title = {{The Model as One Rater Among Several: Measuring Political Positions in Data-Sparse Regions with a Language-Model Panel}},
author = {Tarek Gara},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2606.23042},
eprint = {2606.23042},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2606.23042},
}
RIS
TY - UNPB
TI - The Model as One Rater Among Several: Measuring Political Positions in Data-Sparse Regions with a Language-Model Panel
AU - Tarek Gara
PY - 2026
DA - 2026/10/27
PB - arXiv
DO - 10.48550/arxiv.2606.23042
UR - https://arxiv.org/abs/2606.23042
AB - Most instruments for measuring political positions, such as manifesto coding, expert surveys and text-scaling models, were built and validated on Western party systems, and they break down worst where many consequential actors never publish a manifesto, never contest a competitive election, or commit one position to a charter and act on another in office. This paper proposes a method for such settings. I treat a large language model as a single fallible rater in a panel, the way an expert survey treats one expert, and describe the panel, its synthesis, an applicability rule that keeps a blank distinct from a zero, and a lens that separates what an actor declares from what it does. Three results follow. First, a built-in experiment isolates the rubric: with a definition-free round held fixed, written axis definitions move scores by a mean of 1.8 points on a 21-point scale and tighten agreement between raters (mean absolute gap 2.81 to 2.50; r 0.81 to 0.89). Second, across nine models from eight laboratories in two countries, Krippendorff's alpha is 0.86 on an interval and 0.87 on an ordinal metric, and it held as the panel grew from five raters to nine. This is reliability and says nothing yet about validity, since models trained on overlapping data can share a bias no statistic computed from the models can detect. Third, the panel's sharpest split, a bimodal divergence on an actor's stance toward the state's foundational order, comes from a referent problem: the models agree on the facts and differ on which order counts as the regime. A blind triple-coding traces about two-thirds of such disagreement to interpretation. The worked example is the Middle East and North Africa, and the rubric, prompt and data are released in full.
ER -