Assessing political bias in AI systems: a framework for disentangling viewpoint preferences from epistemic integrity

2026/06/19 by David Rozado, Philip E. Tetlock · 1 voice
Social Sciences · #Computational and Text Analysis Methods #Ethics and Social Impacts of AI #Misinformation and Its Impacts

paper · doi:10.1007/s11186-026-09719-6

crossref issued 2026/06/19 · crossref published 2026/06/19 · crossref published-online 2026/06/19 · openalex publication_date 2026/06/19 · crossref created 2026/06/19 · crossref deposited 2026/06/19 · crossref indexed 2026/06/19 · openalex created_date 2026/06/20 · openalex updated_date 2026/07/23 · crossref published-print 2026/08/01

Citations

• Political diversity will improve social psychological science
• What Drives Media Slant? Evidence From U.S. Daily Newspapers
• Partisan registration of faculty in flagship colleges
• Quantifying and alleviating political bias in language models
• Training language models to follow instructions with human feedback
• Beware ‘persuasive communication devices’ when writing and reading scientific articles
• Direct Preference Optimization: Your Language Model is Secretly a Reward Model
• Exploiting Generative AI to Scale up Intelligent Tutoring Systems
• Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Models
• Cultural bias and cultural alignment of large language models
• Large Language Models Reflect the Ideology of their Creators
• “Turning right”? An experimental study on the political value shift in large language models
• Revealing Political Bias in LLMs through Structured Multi-Agent Debate
• The Hidden Bias: A Study on Explicit and Implicit Political Stereotypes in Large Language Models
• Artificial Barriers to Intelligence - Training Effects on Response Patterns in Large Language Models

Discussions

• Assessing political bias in AI systems: a framework for disentangling viewpoint preferences from epistemic integrity doi.org/10.1007/s111... Rozado & Tetlock 2026 Theor Soc. [bsky, 0 points, 1 comments]