Evidence of political bias in search engines and language models before major elections
2026-03-24 • Computers and Society
Computers and Society
AI summaryⓘ
The authors studied how search engines and large language models (LLMs) show information about politics just before big elections in Europe and the US. They found that some search engines mention far-right groups more often than expected in Europe, while in the US, Google highlights topics important to Republicans and other search engines focus on topics important to Democrats. The answers from LLMs were more balanced but still showed some bias toward far-right and Green groups. This study points out that small biases in these tools might affect democracy and suggests regular checks to understand their fairness.
Search enginesLarge language modelsAlgorithmic biasPolitical informationEuropean Parliament electionUS presidential electionIdeological biasAudit methodologyFar-right politicsDemocratic process
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.