Research

Paper

AI LLM March 24, 2026

Evidence of political bias in search engines and language models before major elections

Authors

Íris Damião, Paulo Almeida, João Franco, Nuno Santos, Pedro C. Magalhães, Joana Gonçalves-Sá

Abstract

Search engines (SEs) and large language models (LLMs) are central to political information access, yet their algorithmic decisions and potential underlying biases remain underexplored. We developed a standardized, privacy-preserving, bot-and-proxy methodology to audit four SEs and two LLMs before the 2024 European Parliament and US presidential elections. We collected answers to approximately 4,360 queries related to elections in five EU countries and 15 US counties, identified political entities and topics in those answers, and mapped them to ideological positions (EU) or issue associations (US). In Europe, SE results disproportionately mentioned far-right entities beyond levels expected from polls, past elections, or media salience. In the US, Google strongly favored topics more important to Republican voters, while other search engines favored issues more relevant to Democrats. LLMs responses were more balanced, although there is evidence of overrepresentation of far-right (and Green) entities. These results show evidence of bias and open important discussions on how even small skews in widely used platforms may influence democratic processes, calling for systematic audits of their outputs.

Metadata

arXiv ID: 2603.23474
Provider: ARXIV
Primary Category: cs.CY
Published: 2026-03-24
Fetched: 2026-03-25 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.23474v1</id>\n    <title>Evidence of political bias in search engines and language models before major elections</title>\n    <updated>2026-03-24T17:39:34Z</updated>\n    <link href='https://arxiv.org/abs/2603.23474v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.23474v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Search engines (SEs) and large language models (LLMs) are central to political information access, yet their algorithmic decisions and potential underlying biases remain underexplored. We developed a standardized, privacy-preserving, bot-and-proxy methodology to audit four SEs and two LLMs before the 2024 European Parliament and US presidential elections. We collected answers to approximately 4,360 queries related to elections in five EU countries and 15 US counties, identified political entities and topics in those answers, and mapped them to ideological positions (EU) or issue associations (US). In Europe, SE results disproportionately mentioned far-right entities beyond levels expected from polls, past elections, or media salience. In the US, Google strongly favored topics more important to Republican voters, while other search engines favored issues more relevant to Democrats. LLMs responses were more balanced, although there is evidence of overrepresentation of far-right (and Green) entities. These results show evidence of bias and open important discussions on how even small skews in widely used platforms may influence democratic processes, calling for systematic audits of their outputs.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CY'/>\n    <published>2026-03-24T17:39:34Z</published>\n    <arxiv:comment>20 pages, 4 figures; Supplementary Information : Page 22 - 74</arxiv:comment>\n    <arxiv:primary_category term='cs.CY'/>\n    <author>\n      <name>Íris Damião</name>\n    </author>\n    <author>\n      <name>Paulo Almeida</name>\n    </author>\n    <author>\n      <name>João Franco</name>\n    </author>\n    <author>\n      <name>Nuno Santos</name>\n    </author>\n    <author>\n      <name>Pedro C. Magalhães</name>\n    </author>\n    <author>\n      <name>Joana Gonçalves-Sá</name>\n    </author>\n  </entry>"
}