Revealing Political Bias in LLMs through Structured Multi-Agent Debate
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909648530964480 |
|---|---|
| author | Bandaru, Aishwarya Bindley, Fabian Bluth, Trevor Chavda, Nandini Chen, Baixu Law, Ethan |
| author_facet | Bandaru, Aishwarya Bindley, Fabian Bluth, Trevor Chavda, Nandini Chen, Baixu Law, Ethan |
| contents | Large language models (LLMs) are increasingly used to simulate social behaviour, yet their political biases and interaction dynamics in debates remain underexplored. We investigate how LLM type and agent gender attributes influence political bias using a structured multi-agent debate framework, by engaging Neutral, Republican, and Democrat American LLM agents in debates on politically sensitive topics. We systematically vary the underlying LLMs, agent genders, and debate formats to examine how model provenance and agent personas influence political bias and attitudes throughout debates. We find that Neutral agents consistently align with Democrats, while Republicans shift closer to the Neutral; gender influences agent attitudes, with agents adapting their opinions when aware of other agents' genders; and contrary to prior research, agents with shared political affiliations can form echo chambers, exhibiting the expected intensification of attitudes as debates progress. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_11825 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Revealing Political Bias in LLMs through Structured Multi-Agent Debate Bandaru, Aishwarya Bindley, Fabian Bluth, Trevor Chavda, Nandini Chen, Baixu Law, Ethan Artificial Intelligence Computers and Society Social and Information Networks Large language models (LLMs) are increasingly used to simulate social behaviour, yet their political biases and interaction dynamics in debates remain underexplored. We investigate how LLM type and agent gender attributes influence political bias using a structured multi-agent debate framework, by engaging Neutral, Republican, and Democrat American LLM agents in debates on politically sensitive topics. We systematically vary the underlying LLMs, agent genders, and debate formats to examine how model provenance and agent personas influence political bias and attitudes throughout debates. We find that Neutral agents consistently align with Democrats, while Republicans shift closer to the Neutral; gender influences agent attitudes, with agents adapting their opinions when aware of other agents' genders; and contrary to prior research, agents with shared political affiliations can form echo chambers, exhibiting the expected intensification of attitudes as debates progress. |
| title | Revealing Political Bias in LLMs through Structured Multi-Agent Debate |
| topic | Artificial Intelligence Computers and Society Social and Information Networks |
| url | https://arxiv.org/abs/2506.11825 |