Political Sorting Can Drive AI Models Apart Through User Feedback

arXiv:2609.28486v1 Announce Type: new Abstract: Large language models are rapidly becoming an important source of political information. This raises a fundamental question: will AI systems support a shared basis for political knowledge, or lead different political groups to rely on increasingly different models? Political sorting can drive model fragmentation if three conditions hold: politically different users select into different models, learning from user feedback pushes those models apart politically, and the resulting differences shape subsequent model choices. We call this self-reinforcing process the Centrifugal Alignment Spiral. We study its components in three steps. First, we draw on a human experiment showing that political identity predicts model choice. Second, we fine-tune language models on synthetic feedback reflecting predominantly Democratic or Republican preferences. Across five independent runs per model family, paired models diverged on 12-41% of unseen survey questions with large partisan gaps, and in every run the differences moved in the expected political direction; for some models, differentiation extended even to issue areas excluded from training. Pooling feedback across groups instead suppressed divergence. Third, an empirically anchored agent-based model shows what follows when political sorting and model adaptation operate together: models attract politically distinct audiences, learn from them, and diverge further. User feedback can therefore turn political sorting among AI users into durable differences between the models on which they rel

AI models may reinforce political polarization

The study finds that user political sorting and feedback cause AI models to diverge politically, reinforcing partisan divides and fragmenting shared knowledge bases. This undermines a common understanding and can exacerbate political polarization. The evidence includes human experiments, controlled model fine-tuning, and agent-based simulations, providing moderately strong support.

The research suggests that AI models, through user feedback, could exacerbate political polarization by diverging along partisan lines, creating distinct information sources for different political groups. This 'Centrifugal Alignment Spiral' would undermine a shared basis for political knowledge and could lead to increased societal fragmentation. The study uses human experiments and agent-based modeling to support its claims.

The paper presents a mechanism by which AI models can diverge politically due to user feedback. This could lead to different political groups relying on different models, fragmenting political knowledge. The evidence is strong, with experimental and modeling results supporting the claims.

SOURCE     arXiv cs.CY (Computers and Society) (tier 1)
   ↓
DOCUMENT   6c2b7dc8-84e3-436b-9654-d46d4e969e94
           https://arxiv.org/abs/2609.28486
   ↓
EVIDENCE   3 extracted excerpts
   ↓
MODEL RUN  5 runs, methodology 1.0.1
   ↓
SCORE      -65  (Strongly adverse)
   ↓
CONFIDENCE 80%