Retrieval-Enhanced Machine Learning: Synthesis and Opportunities

TL;DR

This paper introduces a formal framework for retrieval-enhanced machine learning (REML), synthesizing literature across domains and bridging IR research with modern ML applications to promote interdisciplinary research.

Contribution

It provides a comprehensive, formalized framework for REML, integrating diverse ML domains and connecting IR research with contemporary retrieval-augmented models.

Findings

REML framework unifies various ML applications with retrieval components.

Identifies gaps between IR research and REML studies.

Encourages interdisciplinary research in retrieval-augmented ML.

Abstract

In the field of language modeling, models augmented with retrieval components have emerged as a promising solution to address several challenges faced in the natural language processing (NLP) field, including knowledge grounding, interpretability, and scalability. Despite the primary focus on NLP, we posit that the paradigm of retrieval-enhancement can be extended to a broader spectrum of machine learning (ML) such as computer vision, time series prediction, and computational biology. Therefore, this work introduces a formal framework of this paradigm, Retrieval-Enhanced Machine Learning (REML), by synthesizing the literature in various domains in ML with consistent notations which is missing from the current literature. Also, we found that while a number of studies employ retrieval components to augment their models, there is a lack of integration with foundational Information Retrieval (IR) research. We bridge this gap between the seminal IR research and contemporary REML studies by investigating each component that comprises the REML framework. Ultimately, the goal of this work is to equip researchers across various disciplines with a comprehensive, formally structured framework of retrieval-enhanced models, thereby fostering interdisciplinary future research.