Issue Bias in Generative AI Writing Assistance: Political Issues and LLMs in the Swedish 2026 Election
Abstract
Generative AI writing assistants and the Large Language Models (LLMs) that power them are increasingly part of how voters gather information before elections. With growing evidence that they influence users' opinions, it is increasingly important to understand the views and positions of these tools. To better understand these views, we examine the stances supplied by six LLMs on a variety of Swedish-language writing tasks ahead of the 2026 Swedish parliamentary election. We cross 107 policy propositions with 77 writing templates and neutral, positive, and negative prompt framings, producing 24,717 prompts per model and 148,302 responses. To study these, we look at the models' default stance tendencies, compare how they respond to similar issues, and compare their responses with those of each of Sweden's eight parliamentary parties on the same issue. We find that Claude, DeepSeek, Gemini, and Mistral have similar profiles; ChatGPT more often supplies neutral or ambivalent text; and Grok differs most on topics such as migration, crime, and gender. When comparing the political parties, we find that the Social Democrats are closest to all six models. Still, after correcting for multiple comparisons, none of the within-model differences in party distances remains significant. Overall, we find that no model has a clear preference, nor a clear preference for a party, but that this depends on the specific issue or task the user asks about.
Related
- STV Audit Graphs: A Visual Tool to Measure Election Stability
- Adapting Pairs Trading to Gambling Markets A Case Study of the U.S. Presidential Election
- Fast, cheap and sustainable: armament portfolio arbitration under attrition, lead time and political discontinuity
- Scaffold Write Debug: A Three-Stage Approach to Proof Writing in Introductory Real Analysis
- Classical Commitment over Quantum Channels with Limited Entanglement Assistance
BibTeX
@misc{bruinsma2026issue,
title = {{Issue Bias in Generative AI Writing Assistance: Political Issues and LLMs in the Swedish 2026 Election}},
author = {Bastiaan Bruinsma and Annika Fredén and Paul Röttger and Moa Johansson and Asad Sayeed},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.15207},
eprint = {2609.15207},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.15207},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Issue Bias in Generative AI Writing Assistance: Political Issues and LLMs in the Swedish 2026 Election
AU - Bastiaan Bruinsma
AU - Annika Fredén
AU - Paul Röttger
AU - Moa Johansson
AU - Asad Sayeed
PY - 2026
DA - 2026/09/28
PB - arXiv
DO - 10.48550/arxiv.2609.15207
UR - https://arxiv.org/abs/2609.15207
AB - Generative AI writing assistants and the Large Language Models (LLMs) that power them are increasingly part of how voters gather information before elections. With growing evidence that they influence users' opinions, it is increasingly important to understand the views and positions of these tools. To better understand these views, we examine the stances supplied by six LLMs on a variety of Swedish-language writing tasks ahead of the 2026 Swedish parliamentary election. We cross 107 policy propositions with 77 writing templates and neutral, positive, and negative prompt framings, producing 24,717 prompts per model and 148,302 responses. To study these, we look at the models' default stance tendencies, compare how they respond to similar issues, and compare their responses with those of each of Sweden's eight parliamentary parties on the same issue. We find that Claude, DeepSeek, Gemini, and Mistral have similar profiles; ChatGPT more often supplies neutral or ambivalent text; and Grok differs most on topics such as migration, crime, and gender. When comparing the political parties, we find that the Social Democrats are closest to all six models. Still, after correcting for multiple comparisons, none of the within-model differences in party distances remains significant. Overall, we find that no model has a clear preference, nor a clear preference for a party, but that this depends on the specific issue or task the user asks about.
ER -