# AGRaME: Any-Granularity Ranking with Multi-Vector Embeddings

Source: [AGRaME: Any-Granularity Ranking with Multi-Vector Embeddings](<https://www.sota2.com/research/paper/68fa73501e209131cea5bc69>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T02:47:16.604Z

Authors: Revanth Gangi Reddy, Omar Attia, Yunyao Li, Heng Ji, Saloni Potdar

Published: 2024-05-23T20:04:54.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2405.15028>)

[PDF](<https://arxiv.org/pdf/2405.15028.pdf>)
