Can I read MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning on EtoBox?

MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning by 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 is a scholarly article available to read on EtoBox.

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

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.

Author

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

Published

2022

Language

EN