dorsal/arxiv
View SchemaPolitical Alignment in Large Language Models: A Multidimensional Audit of Psychometric Identity and Behavioral Bias
| Authors | Adib Sakhawat, Tahsin Islam, Takia Farhin, Syed Rifat Raiyan, Hasan Mahmud, Md Kamrul Hasan |
|---|---|
| Categories | |
| ArXiv ID | 2601.06194vv1 |
| URL | https://arxiv.org/abs/2601.06194 |
| License | http://creativecommons.org/licenses/by-nc-sa/4.0/ |
Abstract
As large language models (LLMs) are increasingly integrated into social decision-making, understanding their political positioning and alignment behavior is critical for safety and fairness. This study presents a sociotechnical audit of 26 prominent LLMs, triangulating their positions across three psychometric inventories (Political Compass, SapplyValues, 8 Values) and evaluating their performance on a large-scale news labeling task ($N \approx 27{,}000$). Our results reveal a strong clustering of models in the Libertarian-Left region of the ideological space, encompassing 96.3% of the cohort. Alignment signals appear to be consistent architectural traits rather than stochastic noise ($\eta^2 > 0.90$); however, we identify substantial discrepancies in measurement validity. In particular, the Political Compass exhibits a strong negative correlation with cultural progressivism ($r=-0.64$) when compared against multi-axial instruments, suggesting a conflation of social conservatism with authoritarianism in this context. We further observe a significant divergence between open-weights and closed-source models, with the latter displaying markedly higher cultural progressivism scores ($p<10^{-25}$). In downstream media analysis, models exhibit a systematic "center-shift," frequently categorizing neutral articles as left-leaning, alongside an asymmetric detection capability in which "Far Left" content is identified with greater accuracy (19.2%) than "Far Right" content (2.0%). These findings suggest that single-axis evaluations are insufficient and that multidimensional auditing frameworks are necessary to characterize alignment behavior in deployed LLMs. Our code and data will be made public.
{
"annotation_id": "d172d376-6e5b-46f7-b01d-41307e5c45cf",
"date_created": "2026-02-17T05:53:08.165000Z",
"date_modified": "2026-02-17T05:53:08.165000Z",
"file_hash": "5d2582df5342e027b0981ff948eae63a6c175e61420b8de95fad16208437b283",
"private": false,
"record": {
"abstract": "As large language models (LLMs) are increasingly integrated into social decision-making, understanding their political positioning and alignment behavior is critical for safety and fairness. This study presents a sociotechnical audit of 26 prominent LLMs, triangulating their positions across three psychometric inventories (Political Compass, SapplyValues, 8 Values) and evaluating their performance on a large-scale news labeling task ($N \\approx 27{,}000$). Our results reveal a strong clustering of models in the Libertarian-Left region of the ideological space, encompassing 96.3% of the cohort. Alignment signals appear to be consistent architectural traits rather than stochastic noise ($\\eta^2 \u003e 0.90$); however, we identify substantial discrepancies in measurement validity. In particular, the Political Compass exhibits a strong negative correlation with cultural progressivism ($r=-0.64$) when compared against multi-axial instruments, suggesting a conflation of social conservatism with authoritarianism in this context. We further observe a significant divergence between open-weights and closed-source models, with the latter displaying markedly higher cultural progressivism scores ($p\u003c10^{-25}$). In downstream media analysis, models exhibit a systematic \"center-shift,\" frequently categorizing neutral articles as left-leaning, alongside an asymmetric detection capability in which \"Far Left\" content is identified with greater accuracy (19.2%) than \"Far Right\" content (2.0%). These findings suggest that single-axis evaluations are insufficient and that multidimensional auditing frameworks are necessary to characterize alignment behavior in deployed LLMs. Our code and data will be made public.",
"arxiv_id": "2601.06194",
"authors": [
"Adib Sakhawat",
"Tahsin Islam",
"Takia Farhin",
"Syed Rifat Raiyan",
"Hasan Mahmud",
"Md Kamrul Hasan"
],
"categories": [
"cs.CY",
"cs.AI",
"cs.CL"
],
"license": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
"title": "Political Alignment in Large Language Models: A Multidimensional Audit of Psychometric Identity and Behavioral Bias",
"url": "https://arxiv.org/abs/2601.06194",
"version": "v1"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "8ac6561c-121d-4041-9224-ab47584962d0",
"id": "arXiv Dataset",
"type": "Model",
"variant": "snapshot-2026-01-17",
"version": "0.1.0"
},
"user_id": 1000002
}