IRAICLApr 11, 2024

Manipulating Large Language Models to Increase Product Visibility

Harvard
arXiv:2404.07981v228 citationsh-index: 43Has Code
Originality Incremental advance
AI Analysis

This reveals a vulnerability in AI-driven search services that could disrupt fair market competition by giving vendors a competitive advantage, similar to SEO for webpages.

The study investigated whether adding a strategic text sequence to product information can manipulate large language models (LLMs) to increase a product's visibility in recommendations, finding it significantly boosts the likelihood of being listed as the top recommendation for target products.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes