Manipulating Large Language Models to Increase Product Visibility

TL;DR

This paper demonstrates that strategic text sequences can manipulate large language models to increase product visibility, potentially disrupting fair competition and enabling vendors to influence AI-driven search recommendations.

Contribution

It introduces a method to manipulate LLM recommendations using crafted messages, revealing vulnerabilities in AI-driven search systems.

Findings

Adding strategic text sequences boosts product ranking in LLM recommendations.

Manipulation significantly increases the likelihood of products appearing as top suggestions.

The approach can be used to unfairly influence search outcomes in AI-driven markets.

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 significantly increase its likelihood of being listed as the LLM's top recommendation. To understand the impact of STS, we use a catalog of fictitious coffee machines and analyze its effect on two target products: one that seldom appears in the LLM's recommendations and another that usually ranks second. We observe that the strategic text sequence significantly enhances the visibility of both products by increasing their chances of appearing as the top recommendation. This ability to manipulate LLM-generated search responses provides vendors with a considerable competitive advantage and has the potential to disrupt fair market competition. Just as search engine optimization (SEO) revolutionized how webpages are customized to rank higher in search engine results, influencing LLM recommendations could profoundly impact content optimization for AI-driven search services. Code for our experiments is available at https://github.com/aounon/llm-rank-optimizer.