XTR meets ColBERTv2: Adding ColBERTv2 Optimizations to XTR

XTR (Lee et al., 2023) introduced an efficient multi-vector retrieval method that addresses the limitations of the ColBERT (Khattab and Zaharia, 2020) model by simplifying retrieval into a single stage through a modified learning objective. While XTR eliminates the need for multistage retrieval, it doesn’t incorporate the efficiency optimizations from ColBERTv2 (Santhanam et al., 2022), which improve indexing and retrieval speed. In this work, we enhance XTR by integrating ColBERTv2’s optimizations, showing that the combined approach preserves the strengths of both models. This results in a more efficient and scalable solution for multi-vector retrieval, while maintaining XTR’s streamlined retrieval process. We have released the code as an addition to the PrimeQA (PrimeQA, 2023) toolkit.