analiza aiqbench
This experiment with 563 Swiss participants suggests that people's existing attitudes shape how they phrase questions to chatbots, so the chatbot's answers may reinforce rather than correct those attitudes. The finding that attitude-consistent AI responses did not further increase this selectivity is useful, though the study covers one country and one policy domain. For readers tracking how generative AI affects political information-seeking, the work points to user prompting behaviour as a channel for bias that is separate from model outputs.
Discussing politics with a chatbot: How political beliefs shape prompt formulation for generative AI
arXiv:2611.01153v1 Announce Type: cross Abstract: By generating comprehensive and highly personalized answers to user prompts, AI chatbots such as ChatGPT and Gemini can serve as alternatives to search engines and substantially transform online information seeking. However, little research has examined how users interact with these tools to find information, particularly about politics. In this experiment, we examine how Swiss citizens (N = 563) formulate prompts to search for migration-related issues using AI chatbots and whether this process is affected by selective exposure. We find evidence of attitude-consistent prompting, whereby participants who were more critical of migration were more likely to formulate prompts with an anti-migration stance. This effect was stronger for a broad topic (migration in general) than for a specific one (anti-migration popular initiative put to a vote in Switzerland). However, exposure to an attitude-consistent AI response did not further amplify selectivity in prompting. We also did not find evidence that either AI attitudes or thinking styles moderated selectivity in prompting. These findings contribute to the understanding of selective exposure via AI chatbots and the use of generative AI for political information-seeking.
Abstract:By generating comprehensive and highly personalized answers to user prompts, AI chatbots such as ChatGPT and Gemini can serve as alternatives to search engines and substantially transform online information seeking. However, little research has examined how users interact with these tools to find information, particularly about politics. In this experiment, we examine how Swiss citizens (N = 563) formulate prompts to search for migration-related issues using AI chatbots and whether this process is affected by selective exposure. We find evidence of attitude-consistent prompting, whereby participants who were more critical of migration were more likely to formulate prompts with an anti-migration stance. This effect was stronger for a broad topic (migration in general) than for a specific one (anti-migration popular initiative put to a vote in Switzerland). However, exposure to an attitude-consistent AI response did not further amplify selectivity in prompting. We also did not find evidence that either AI attitudes or thinking styles moderated selectivity in prompting. These findings contribute to the understanding of selective exposure via AI chatbots and the use of generative AI for political information-seeking.
Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI)
arXiv:2611.01153 [cs.HC]
(or arXiv:2611.01153v1 [cs.HC] for this version)
https://doi.org/10.48550/arXiv.2611.01153 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 275 cuvinte
Subiecte conexe
Plant-Inspired AI: Plants as Inspiration for Novel Problem Formulations, and Two Case Studies
arXiv · 1 sept. 2026
Generative AI in Turbulence: Foundations, Applications, Validations and Benchmarks
arXiv · 27 oct. 2026
Random Matrix Theory for Chaotic Wave Scattering and Transport
arXiv · 10 iun. 2026
A Survey of Freshness-Aware Wireless Networking with Reinforcement Learning
arXiv · 3 nov. 2026