flâneur

On the Theoretical Limitations of Embedding-Based Retrieval

arxiv.org · 8,694 words · saved by 1 readers

Vector embeddings have been tasked with an ever-increasing set of retrieval tasks over the years, with a nascent rise in using them for reasoning, instruction-following, coding, and more. These new benchmarks push embeddings to work for any query and any notion of relevance that could be given. While prior works have pointed out theoretical limitations of vector embeddings, there is a common assumption that these difficulties are exclusively due to unrealistic queries, and those that are not can be overcome with better training data and larger models. In this work, we demonstrate that we may encounter these theoretical limitations in realistic settings with extremely simple queries. We connect known results in learning theory, showing that the number of top- 𝑘 subsets of documents capable of being returned as the result of some query is limited by the dimension of the embedding. We empirically show that this holds true even if we directly optimize on the test set with free parameteri

Orion Weller Michael Boratko Affiliation: Google DeepMind Email: jinhyuklee@google.com Iftekhar Naim Affiliation: Google DeepMind Jinhyuk Lee Affiliation: Google DeepMind Abstract Vector embeddings have been tasked with an ever-increasing set of retrieval tasks over the years, with a nascent rise in using them for reasoning, instruction-following, coding, and more. These new benchmarks push embeddings to work for any query and any notion of relevance that could be given. While prior works have pointed out theoretical limitations of vector embeddings, there is a common assumption…

saved by

related reading