# Modular Retrieval for Generalization and Interpretation

arXiv: https://arxiv.org/abs/2303.13419 · HTML: https://mlsanity.com/paper/2303.13419/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Mar 2023.

## Built on by (most cited first, 1 of 1)

- [MeVe: A Modular System for Memory Verification and Effective Context Control in Language Models](https://mlsanity.com/paper/2509.01514/) (2025)

## Abstract (arXiv)

New retrieval tasks have always been emerging, thus urging the development of new retrieval models. However, instantiating a retrieval model for each new retrieval task is resource-intensive and time-consuming, especially for a retrieval model that employs a large-scale pre-trained language model. To address this issue, we shift to a novel retrieval paradigm called modular retrieval, which aims to solve new retrieval tasks by instead composing multiple existing retrieval modules. Built upon the paradigm, we propose a retrieval model with modular prompt tuning named REMOP. It constructs retrieval modules subject to task attributes with deep prompt tuning, and yields retrieval models subject to tasks with module composition. We validate that, REMOP inherently with modularity not only has appealing generalizability and interpretability in preliminary explorations, but also achieves comparable performance to state-of-the-art retrieval models on a zero-shot retrieval benchmark.footnoteOur code is available at urlhttps://github.com/FreedomIntelligence/REMOP