most citedToolformer: Language Models Can Teach Themselves to Use Tools

400 citations · 792 across the 12 of their papers we have counts for

collaborators
Showing cs.CLShow all

5 papers · 1 filter

cs.CL2024

TOOLVERIFIER: Generalization to New Tools via Self-Verification

Dheeraj Mekala, Jason Weston, Jack Lanchantin +4

Teaching language models to use tools is an important milestone towards building general assistants, but remains an open problem. While there has been significant progress on learn…

cs.CL202342 cited

Chain-of-Verification Reduces Hallucination in Large Language Models

Shehzaad Dhuliawala, Mojtaba Komeili, Jing Xu +4

Generation of plausible yet incorrect factual information, termed hallucination, is an unsolved issue in large language models. We study the ability of language models to deliberat…

cs.CL2023180 cited

Challenges and Applications of Large Language Models

Jean Kaddour, Joshua Harris, Maximilian Mozes +3

Large Language Models (LLMs) went from non-existent to ubiquitous in the machine learning discourse within a few years. Due to the fast pace of the field, it is difficult to identi…

cs.CL2023143 cited

Augmented Language Models: a Survey

Grégoire Mialon, Roberto Dessì, Maria Lomeli +10

This survey reviews works in which language models (LMs) are augmented with reasoning skills and the ability to use tools. The former is defined as decomposing a potentially comple…

cs.CL2023400 cited

Toolformer: Language Models Can Teach Themselves to Use Tools

Timo Schick, Jane Dwivedi-Yu, Roberto Dessì +5

Language models (LMs) exhibit remarkable abilities to solve new tasks from just a few examples or textual instructions, especially at scale. They also, paradoxically, struggle with…