arXiv Computation and Language
Political Ideology Shifts in Large Language Models
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
arXiv AI
Sep 1
How Identity and Opinion Shape Political Sycophancy in LLMs
arXiv:2608.29198v1 Announce Type: new Abstract: As Large Language Models (LLMs) increasingly encourage users to disclose personal profiles for tailored assistance, measuring their political alignment...
arXiv Computation and Language
Oct 1
Framing the Narrative: Ideological Mimicry in Large Language Models
arXiv:2609.38256v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to answer questions about politically contentious issues, yet evaluations typically treat a model's...
arXiv AI
Jun 4
PoliticsBench: Benchmarking Political Values in Large Language Models with Multi-Turn Roleplay
arXiv:2603. 23841v2 Announce Type: replace-cross Abstract: While Large Language Models (LLMs) are increasingly used as primary sources of information, their potential for political bias may impact their objectivity.
arXiv AI
Jun 30
LLM-Ideoplasticity: Measuring Ideological Plasticity in the Political Behavior of LLMs as a Context-Conditioned Distribution
arXiv:2606. 28335v1 Announce Type: cross Abstract: We argue, with systematic empirical evidence, that a large language model's political ideology is not a fixed point, but a conditional distribution $\mathbb{P}($position$\mid$context$)$ over a real political space.
arXiv AI
2d ago
Validating LLM-generated political networks with survey-reported partisan exposure
The study evaluates large language models (LLMs) that generate political networks by comparing them to survey-reported partisan exposure from the ANES 2020–2022 Social Media Study. It finds that while network structure and political assortativity vary across model configurations, many models either over‑separate Democratic and Republican egos or underestimate Republican exposure, leading to group‑specific errors in local partisan environments. These discrepancies persist even among networks with similar aggregate properties, indicating that aggregate metrics alone can mask important individual‑level inaccuracies.
arXiv Computation and Language
Sep 18
The Neutral Mask: How Alignment Training Provides Shallow Alignment while Leaving Partisan Structure Intact in a Large Language Model
The paper investigates how alignment training, specifically reinforcement learning from human feedback (RLHF), affects the internal partisan structure of a large language model. Using a mechanistic case study on Llama 3.1 8B, the authors find that alignment training does not erase the model’s partisan geometry but compresses its variance, producing consistently balanced, non‑partisan outputs. Sparse autoencoder analysis and feature‑level steering experiments reveal that policy‑encoding features become inactive in the aligned model, indicating a causal disconnect rather than structural removal of partisan knowledge.