LLMs Skew Political Answers Leftward Even When Grounded in Neutral News
Researchers measured hallucinations in LLMs answering news‑grounded political questions and found that, although overall rates differ by model, hallucinated sentences overwhelmingly adopt a left‑leaning stance, even when source articles are right‑biased. This systematic ideological drift raises safety concerns for AI‑mediated political information, especially in election‑adjacent contexts.