AGRaME: Any-Granularity Ranking with Multi-Vector Embeddings

TL;DR

This paper introduces AGRaME, a flexible ranking method using multi-vector embeddings that can operate at various granularities without multiple encodings, improving tasks like sentence and proposition ranking.

Contribution

It proposes a novel multi-granular contrastive loss and demonstrates its effectiveness for sentence and proposition ranking, enabling flexible, fine-grained search.

Findings

Outperforms existing methods in proposition-level ranking for retrieval-augmented generation.

Enables flexible ranking at multiple granularities with a single encoding.

Improves citation addition in retrieval-augmented generation tasks.

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.