MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning

• Main Authors: Karpas, Ehud, Abend, Omri, Belinkov, Yonatan, Lenz, Barak, Lieber, Opher, Ratner, Nir, Shoham, Yoav, Bata, Hofit, Levine, Yoav, Leyton-Brown, Kevin, Muhlgay, Dor, Rozen, Noam, Schwartz, Erez, Shachaf, Gal, Shalev-Shwartz, Shai, Shashua, Amnon, Tenenholtz, Moshe
• Format: Journal Article
• Language: English
• Published: 01-05-2022
• Subjects: Computer Science - Artificial Intelligence; Computer Science - Computation and Language
• DOI: 10.48550/arxiv.2205.00445

Huge language models (LMs) have ushered in a new era for AI, serving as a
gateway to natural-language-based knowledge tasks. Although an essential
element of modern AI, LMs are also inherently limited in a number of ways. We
discuss these limitations and how they can be avoided by adopting a systems
approach. Conceptualizing the challenge as one that involves knowledge and
reasoning in addition to linguistic processing, we define a flexible
architecture with multiple neural models, complemented by discrete knowledge
and reasoning modules. We describe this neuro-symbolic architecture, dubbed the
Modular Reasoning, Knowledge and Language (MRKL, pronounced "miracle") system,
some of the technical challenges in implementing it, and Jurassic-X, AI21 Labs'
MRKL system implementation.