Modular Retrieval For Generalization And Interpretation

Abstract

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.\footnote\{Ou

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyliang2023modular

Related papers

• Generalization Properties Of Retrieval-based Models (2022)0.00
• Retrieval-augmented Dynamic Prompt Tuning For Incomplete Multimodal Learning (2025)8.87
• Colbert-xm: A Modular Multi-vector Representation Model For Zero-shot Multilingual Information Retrieval (2024)0.00
• Lamra: Large Multimodal Model As Your Advanced Retrieval Assistant (2024)7.50
• Parameter-efficient Prompt Tuning Makes Generalized And Calibrated Neural Text Retrievers (2022)5.84
• Fine-grained Retrieval Prompt Tuning (2022)10.07
• CREM: Compression-driven Representation Enhancement For Multimodal Retrieval And Comprehension (2026)0.00
• Freeret: Mllms As Training-free Retrievers (2025)0.00