Reliable, Adaptable, and Attributable Language Models with Retrieval

TL;DR

This paper advocates for retrieval-augmented language models as a more reliable, adaptable, and attributable alternative to traditional parametric models, emphasizing the need for improved interaction, infrastructure, and broader application.

Contribution

It proposes a roadmap for developing general-purpose retrieval-augmented language models, addressing current limitations and infrastructure challenges.

Findings

Retrieval-augmented LMs can improve reliability and adaptability.

Current models struggle with leveraging helpful text beyond knowledge tasks.

Infrastructure development is crucial for scaling retrieval-augmented LMs.

Abstract

Parametric language models (LMs), which are trained on vast amounts of web data, exhibit remarkable flexibility and capability. However, they still face practical challenges such as hallucinations, difficulty in adapting to new data distributions, and a lack of verifiability. In this position paper, we advocate for retrieval-augmented LMs to replace parametric LMs as the next generation of LMs. By incorporating large-scale datastores during inference, retrieval-augmented LMs can be more reliable, adaptable, and attributable. Despite their potential, retrieval-augmented LMs have yet to be widely adopted due to several obstacles: specifically, current retrieval-augmented LMs struggle to leverage helpful text beyond knowledge-intensive tasks such as question answering, have limited interaction between retrieval and LM components, and lack the infrastructure for scaling. To address these, we propose a roadmap for developing general-purpose retrieval-augmented LMs. This involves a reconsideration of datastores and retrievers, the exploration of pipelines with improved retriever-LM interaction, and significant investment in infrastructure for efficient training and inference.