The article explores the impact of Large Language Models (LLMs) on conversational search systems. The study conducts two experiments to investigate whether and how LLM-powered conversational search increases selective exposure compared to conventional search and how LLMs with opinion biases affect this. The findings reveal that users engage in more biased information querying with LLM-powered conversational search, especially when the LLM reinforces their views. These results have significant implications for the development of LLMs and conversational search systems and the policies governing these technologies.
Publication date: 9 Feb 2024
Project Page: https://doi.org/10.1145/3613904.3642459
Paper: https://arxiv.org/pdf/2402.05880
