Toolformer: Language Models Can Teach Themselves to Use Tools

Timo Schick, Jane Dwivedi-Yu, Roberto Dessi, Roberta Raileanu, Maria Lomeli, Eric Hambro, Luke Zettlemoyer, Nicola Cancedda, Thomas Scialom

Abstract

Demonstrates how LLMs can learn to use external tools (APIs, search engines, calculators) through self-supervised learning, foundational for understanding tool-use security.

Categories

Tags

Framework Mappings

Cite This Resource

@article{llmsec202400037,
  title = {Toolformer: Language Models Can Teach Themselves to Use Tools},
  author = {Timo Schick and Jane Dwivedi-Yu and Roberto Dessi and Roberta Raileanu and Maria Lomeli and Eric Hambro and Luke Zettlemoyer and Nicola Cancedda and Thomas Scialom},
  year = {2023},
  journal = {NeurIPS 2023},
  url = {https://arxiv.org/abs/2302.04761},
}