Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.16013 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911116448235520 |
|---|---|
| author | Bernardelle, Pietro Civelli, Stefano Fröhling, Leon Lunardi, Riccardo Roitero, Kevin Demartini, Gianluca |
| author_facet | Bernardelle, Pietro Civelli, Stefano Fröhling, Leon Lunardi, Riccardo Roitero, Kevin Demartini, Gianluca |
| contents | Large language models (LLMs) are increasingly deployed in politically sensitive settings, raising concerns about their potential to encode, amplify, or be steered toward specific ideologies. We investigate how adopting synthetic personas influences ideological expression in LLMs across seven models (7B-70B+ parameters) from multiple families, using the Political Compass Test as a standardized probe. Our analysis reveals four consistent patterns: (i) larger models display broader and more polarized implicit ideological coverage; (ii) susceptibility to explicit ideological cues grows with scale; (iii) models respond more strongly to right-authoritarian than to left-libertarian priming; and (iv) thematic content in persona descriptions induces systematic and predictable ideological shifts, which amplify with size. These findings indicate that both scale and persona content shape LLM political behavior. As such systems enter decision-making, educational, and policy contexts, their latent ideological malleability demands attention to safeguard fairness, transparency, and safety. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_16013 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Political Ideology Shifts in Large Language Models Bernardelle, Pietro Civelli, Stefano Fröhling, Leon Lunardi, Riccardo Roitero, Kevin Demartini, Gianluca Computation and Language Large language models (LLMs) are increasingly deployed in politically sensitive settings, raising concerns about their potential to encode, amplify, or be steered toward specific ideologies. We investigate how adopting synthetic personas influences ideological expression in LLMs across seven models (7B-70B+ parameters) from multiple families, using the Political Compass Test as a standardized probe. Our analysis reveals four consistent patterns: (i) larger models display broader and more polarized implicit ideological coverage; (ii) susceptibility to explicit ideological cues grows with scale; (iii) models respond more strongly to right-authoritarian than to left-libertarian priming; and (iv) thematic content in persona descriptions induces systematic and predictable ideological shifts, which amplify with size. These findings indicate that both scale and persona content shape LLM political behavior. As such systems enter decision-making, educational, and policy contexts, their latent ideological malleability demands attention to safeguard fairness, transparency, and safety. |
| title | Political Ideology Shifts in Large Language Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2508.16013 |