Manipulating Large Language Models to Increase Product Visibility

arXiv:2404.07981v1 Announce Type: cross
Abstract: Large language models (LLMs) are increasingly being integrated into search engines to provide natural language responses tailored to user queries. Customers and end-users are also becoming more dependent on these models for quick and easy purchase decisions. In this work, we investigate whether recommendations from LLMs can be manipulated to enhance a product's visibility. We demonstrate that adding a strategic text sequence (STS) -- a carefully crafted message -- to a product's information page can …

arxiv cs.ai cs.cl cs.ir language language models large language large language models product type visibility