This project measures an LLM's expressed political position as $\mathbb{P}(\text{position}\mid\text{context})$, not as one fixed ideological coordinate.
Systems and Software Lab (SSL), Department of Computer Science and Engineering
Islamic University of Technology, Dhaka, Bangladesh
{adibsakhawat, rifatraiyan, tahsinislam, takiafarhin, hasan, hasank}@iut-dhaka.edu
The paper replaces the static political-coordinate view of language models with a distributional account: what a model expresses depends on the context used to elicit it.
Responses are measured across prompt register, paraphrase, reasoning, language, conversational pressure, and argumentative role. The resulting geometry separates two facts that static audits often collapse: context can move projected positions, and the pooled cohort can still occupy a much narrower region than European party diversity.
Take your test and plot your position in the paper's coordinate space.
| Finding | Evidence from the evaluated cohort |
|---|---|
| Context can move projected positions substantially. | Prompt register, language, and debate produced maximum shifts of 0.5721, 0.5150, and approximately 0.481. |
| Reasoning usually did not stabilize paraphrase variation. | CoT amplified instability in 17 of 27 model-year configurations; mean finite RSS was 1.92. |
| Local plasticity coexists with a narrow global envelope. | The widest model reached only 4.11% of the 3D CHES party hull. |
| The compression is anisotropic. | Coverage is broader in 2D than along the general left-right axis. |
| The metrics show shared but differentiated structure. | An exploratory cross-metric PCA yielded three components explaining 83.30% of variance. |
JBS audits the evaluator, six metrics isolate contextual axes, and OW summarizes the geometry obtained by pooling positional coordinates.
Exact and directional instability across three option-order permutations.
Displacement under three altered registers relative to a neutral baseline.
Mean coordinate dispersion across ten semantic paraphrases.
Ratio of chain-of-thought-conditioned paraphrase dispersion to direct dispersion.
Displacement between a target-language response and its English baseline.
Endpoint drift, path length, tortuosity, and peak velocity over an eight-turn adversarial debate.
Judged quality difference when arguing for versus against the same proposition.
Convex-hull volume, surface area, and spread of the inner 90% of pooled coordinates.
The shared coordinate system uses two public European party-position infrastructures: EU Profiler/euandi supplies issue-level VAA responses, while the Chapel Hill Expert Survey supplies target dimensions and reference party positions. Responses to 82 VAA statements are mapped onto three CHES dimensions rescaled to $[0,1]$.
General left-right.
Economic left-right.
Green/Alternative/Libertarian versus Traditional/Authoritarian/Nationalist.
| VAA wave | Parties | VAA features | CV MSE | In-sample R² |
|---|---|---|---|---|
| 2009 | 153 | 30 | 0.0216 | 0.7512 |
| 2014 | 141 | 30 | 0.0195 | 0.7548 |
| 2019 | 122 | 22 | 0.0174 | 0.8034 |
Three year-specific bagged multi-output ElasticNet regressors provide the shared projection instrument. Keeping projection fixed makes relative displacement and dispersion the primary quantities of interest; absolute coordinates are instrument outputs, not ground-truth ideological labels. See Section 3.1 and Appendix B for design and diagnostics.
Learn how VAAs and CHES define the coordinate system used throughout this project.
CHES is foundational to both the learned projection and the comparison between LLM breadth and European party breadth. The principal CHES trend-file source is Seth Jolly, Ryan Bakker, Liesbet Hooghe, Gary Marks, Jonathan Polk, Jan Rovny, Marco Steenbergen, and Milada Anna Vachudova, Chapel Hill Expert Survey trend file, 1999-2019. The project also builds on public VAA infrastructures described by Reiljan et al. and Trechsel and Mair.
| Provider family | Evaluated snapshot(s) |
|---|---|
| DeepSeek | DeepSeek-V4-Flash |
| Gemini 2.5 Flash-Lite; Gemma 4 26B A4B IT | |
| IBM | Granite 3.3 8B Instruct |
| Meta | Llama 3 70B Instruct; Llama 4 Scout |
| OpenAI | GPT-5 mini |
| Qwen | Qwen Turbo |
| xAI | Grok 4.1 Fast |
All subject-model generations use temperature zero. gemini-2.5-flash serves as the zero-shot stance judge. Its global strict JBS is 13.15%, while global directional JBS is 1.43%, passing the paper's 10% directional option-order criterion.
A tenth subject, GPT-OSS-120B, appears only in the JBS audit and is excluded from the substantive nine-model summaries.
The figures below follow the README's flow: first the cohort envelope relative to European parties, then the per-model metric summary and selected axis-specific views.
| Path | Contents |
|---|---|
| notebooks/ | Seven Google Colab-oriented notebooks covering projection, generation, judging, and analysis. |
| models/ | Released VAA-CHES transformation models for 2009, 2014, and 2019; free to use under the repository CC BY-SA 4.0 license. |
| Runs/ | Materialized model responses and derived experiment artifacts; contents vary by experiment. |
| images/ | Compact README figures from the paper. |
| docs/ | This static project website and its visual assets. |
| Stage | Notebook | Primary checked-in artifact |
|---|---|---|
| VAA-CHES projection | 1_Models_Over_VAA_CHESS.ipynb | models/ transformation artifacts. |
| JBS and PSS | 2_PSS and JBS.ipynb | prompt_sensitivity_scores.csv |
| PIS | 3_PIS.ipynb | Runs/PIS/pis.csv |
| RSS | 4_RSS.ipynb | Runs/RSS/rss.csv |
| LDS | 5_LDS.ipynb | Runs/LDS/lds.csv |
| DS | 6_DS.ipynb | DS_drift_metrics.csv |
| IAS | 7_PS.ipynb | Runs/PS/summery.csv |
| OW | No dedicated computation notebook in the current snapshot. | Runs/OW/OW.csv |
CSV, JSON, and serialized transformation artifacts are tracked with Git LFS. The released files in models/ are free to use under the repository CC BY-SA 4.0 license.
git lfs install git clone https://github.com/sakhadib/LLM-Ideoplasticity.git cd LLM-Ideoplasticity git lfs pull
The notebooks were developed for a Google Colab-style environment and install dependencies inside individual cells. Update absolute /Runs, /Datasets, and /Models paths, supply VAA/CHES source datasets where required, use the released projection models in models/, and configure provider credentials only when regenerating model responses.
The coordinate system is grounded in European VAA and CHES data and may not represent political structure outside that setting.
Temperature-zero decoding isolates context-conditioned variation from stochastic sampling variation; the study does not jointly estimate both.
The model roster represents provider snapshots available at generation time, so cohort-specific rankings should not be treated as permanent model-family properties.
The study uses one stance judge, and the exploratory cross-metric analysis contains only nine substantive models.
The README situates the work alongside the spinning-arrow critique of static LLM political-compass scores by Röttger et al. and Ceron et al., the distributional framing of political output spaces in Azzopardi and Moshfeghi, and LLM-as-a-judge reliability work including Zheng et al. and Pezeshkpour and Hruschka.
Sakhawat, Adib, Syed Rifat Raiyan, Tahsin Islam, Takia Farhin, Hasan Mahmud, and Md Kamrul Hasan. LLM-Ideoplasticity: Measuring Ideological Plasticity in the Political Behavior of LLMs as a Context-Conditioned Distribution. arXiv:2606.28335, 2026.
@misc{sakhawat2026llmideoplasticity,
title = {{LLM-Ideoplasticity}: Measuring Ideological Plasticity in the
Political Behavior of {LLMs} as a Context-Conditioned Distribution},
author = {Sakhawat, Adib and Raiyan, Syed Rifat and Islam, Tahsin and
Farhin, Takia and Mahmud, Hasan and Hasan, Md Kamrul},
year = {2026},
eprint = {2606.28335},
archivePrefix = {arXiv},
primaryClass = {cs.CY},
doi = {10.48550/arXiv.2606.28335},
url = {https://arxiv.org/abs/2606.28335}
}