On the Merits of LLM-Based Corpus Enrichment

Generative AI (genAI) technologies -- specifically, large language models (LLMs) -- and search have evolving relations. We argue for a novel perspective: using genAI to enrich a document corpus so as to improve query-based retrieval effectiveness. The enrichment is based on modifying existing documents or generating new ones. As an empirical 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) and answer attribution in question answering.

@article{zur2025_2506.06015,
  title={ On the Merits of LLM-Based Corpus Enrichment },
  author={ Gal Zur and Tommy Mordo and Moshe Tennenholtz and Oren Kurland },
  journal={arXiv preprint arXiv:2506.06015},
  year={ 2025 }
}