GEM: A Generative Embedding Model Bridging Reasoning and Retrieval

Excerpt

arXiv:2608.13200v2 Announce Type: replace-cross Abstract: Modern LLMs excel at reasoning and instruction following, enabling users to express complex and diverse information needs. However, conventional retrievers largely rely on surface-level matching between queries and documents, resulting in a growing gap between how users express their needs and how retrievers interpret them. In this paper, we present GEM, a generative embedding model that augments retrieval through its own knowledge by exp