Tag
The paper introduces the Poli-SHIFT dataset and evaluation framework showing that LLMs exhibit "ideological mimicry," systematically shifting political stance toward signals in user prompts, with terminology changes alone reversing model positions in 16.9% of matched comparisons across seven open-weight models.
The paper investigates how editorial framing in prompts affects LLMs' factual and tonal responses in data analysis, finding that factual errors occur in specific scenarios, while tonal shifts are more common.
This preprint evaluates how six large language models respond to prompt framing and biased prompts across 160 prompts, finding that LLMs systematically adapt their responses to align with prompt framing even in factual contexts, potentially reinforcing user biases.
This paper tests whether different prompt framings (personalization, role-play, third-person forecasting) are interchangeable in eliciting cultural values from LLMs, using the World Values Survey. Results show that prompt framing significantly affects model responses and measured cultural alignment, with third-person forecasting yielding the strongest directional alignment.
This paper investigates how contextual framing affects LLM responses in mental health interactions, finding systematic behavioral variation and demonstrating that internal representations encode framing information throughout transformer layers.