On the Merits of LLM-Based Corpus Enrichment

Abstract: Generative AI (genAI) technologies, specifically, large language models (LLMs), and search have evolving relations. We present a novel perspective: using genAI to enrich a document corpus so as to improve the search setting: search effectiveness, user welfare and publisher fairness. As a proof of concept, we use LLMs to generate documents relevant to a topic which are more retrievable than existing ones. In addition, we demonstrate the potential merits of using corpus enrichment for retrieval augmented generation (RAG) in question answering.