2 papers
cs.CY2026
Political Sorting Can Drive AI Models Apart Through User Feedback
Petter Törnberg, Michael Heseltine, Nicolò Pagan +3
Large language models are rapidly becoming an important source of political information. This raises a fundamental question: will AI systems support a shared basis for political kn…
cs.AI2026
Political Bias Audits of LLMs Capture Sycophancy to the Inferred Auditor
Petter Törnberg, Michelle Schimmel
Large language models (LLMs) are commonly evaluated for political bias based on their responses to fixed questionnaires, which typically place frontier models on the political left…