AGRaME: Any-Granularity Ranking with Multi-Vector Embeddings
Abstract
Ranking is a fundamental and popular problem in search. However, existing ranking algorithms usually restrict the granularity of ranking to full passages or require a specific dense index for each desired level of granularity. Such lack of flexibility in granularity negatively affects many applications that can benefit from more granular ranking, such as sentence-level ranking for open-domain question-answering, or proposition-level ranking for attribution. In this work, we introduce the idea of any-granularity ranking, which leverages multi-vector embeddings to rank at varying levels of granularity while maintaining encoding at a single (coarser) level of granularity. We propose a multi-granular contrastive loss for training multi-vector approaches, and validate its utility with both sentences and propositions as ranking units. Finally, we demonstrate the application of proposition-level ranking to post-hoc citation addition in retrieval-augmented generation, surpassing the performance of prompt-driven citation generation.
Cite
@article{arxiv.2405.15028,
title = {AGRaME: Any-Granularity Ranking with Multi-Vector Embeddings},
author = {Revanth Gangi Reddy and Omar Attia and Yunyao Li and Heng Ji and Saloni Potdar},
journal= {arXiv preprint arXiv:2405.15028},
year = {2024}
}