Retrieval-Enhanced Machine Learning

By Hamed Zamani, Fernando Diaz, Mostafa Dehghani, Donald Metzler, Michael Bendersky. 2022

75 citations recorded by the source corpus.

Although information access systems have long supportedpeople in accomplishing a wide range of tasks, we propose broadening the scope of users of information access systems to include task-driven machines, such as machine learning models. In this way, the core principles of indexing, representation, retrieval, and ranking can be applied and extended to substantially improve model generalization, scalability, robustness, and interpretability. We describe a generic retrieval-enhanced machine learning (REML) framework, which includes a number of existing models as special cases. REML challenges information retrieval conventions, presenting opportunities for novel advances in core areas, including optimization. The REML research agenda lays a foundation for a new style of information access research and paves a path towards advancing machine learning and artificial intelligence.

Subfields: Artificial Intelligence, Information Systems, Retrieval-Augmented Generation, Information Retrieval & Search

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

In Retrieval-Augmented Generation

In Information Retrieval & Search

Citations in the corpus

Multi-Task Retrieval-Augmented Text Generation with Relevance Sampling (2022, methodology): “On the other hand, this setup brings additional complexity to the text generation tasks, as we now administer connections of a query-answer pair to relevant items in the knowledge base, for a more holistic view including retrieval performance (Zamani et al., 2022).”