一作SIGIR 2026Oral· Information Retrieval (Full)
Benchmarking Filtered Approximate Nearest Neighbor Search Algorithms on Transformer-based Embedding Vectors
Patrick Iff · Paul Brügger · Marcin Chrapek · David Kochergin · Maciej Besta · Torsten Hoefler
摘要
Advances in embedding models for text, image, audio, and video drive progress across multiple domains, including retrieval-augmented generation, recommendation systems, and others. Many of these applications require an efficient method to retrieve items that are close to a given query in the embe...