Skip to content
Search
paperFebruary 2023ReviewedOpen access

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

NeurIPS 2023

View resourcePDF

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

Tool Use SecurityAgent Architecture
#tool-use#API-calling#foundational

Framework mappings

OWASP Top 10 for LLM Applications
  • LLM06Excessive Agency
OWASP Top 10 for Agentic Applications
  • ASI02Tool Misuse & Exploitation

Cite

@inproceedings{schick2023toolformer,
  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},
  month = feb,
  booktitle = {NeurIPS 2023},
  eprint = {2302.04761},
  archivePrefix = {arXiv},
  doi = {10.52202/075280-2997},
  url = {https://arxiv.org/abs/2302.04761}
}