Projection and Quantisation: A Unifying View of Learning to Hash, from Random Projections to the RAG Era
A new research paper proposes a unifying framework called Projection-Quantisation-Organisation (PQO) to understand and predict methods in approximate nearest neighbour search. This framework categorizes existing techniques, including those used in retrieval-augmented generation for large language models, based on three core design choices: projection placement, quantisation thresholds, and code organisation. The research highlights that memory efficiency is primarily gained through quantisation, and that code quality improves significantly with available supervision. AI
IMPACT This framework could streamline the development and understanding of retrieval systems crucial for grounding large language models.