activity
20222024
most citedToolformer: Language Models Can Teach Themselves to Use Tools

400 citations · 788 across the 7 of their papers we have counts for

collaborators
Showing cs.CLShow all

6 papers · 1 filter

cs.CL2024

FairPair: A Robust Evaluation of Biases in Language Models through Paired Perturbations

Jane Dwivedi-Yu, Raaz Dwivedi, Timo Schick

The accurate evaluation of differential treatment in language models to specific groups is critical to ensuring a positive and safe user experience. An ideal evaluation should have…

cs.CL2023

Evaluation of Faithfulness Using the Longest Supported Subsequence

Anirudh Mittal, Timo Schick, Mikel Artetxe +1

As increasingly sophisticated language models emerge, their trustworthiness becomes a pivotal issue, especially in tasks such as summarization and question-answering. Ensuring thei…

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…

cs.CL202244 cited

PEER: A Collaborative Language Model

Timo Schick, Jane Dwivedi-Yu, Zhengbao Jiang +7

Textual content is often the output of a collaborative writing process: We start with an initial draft, ask for suggestions, and repeatedly make changes. Agnostic of this process,…

cs.CL2022201 cited

Atlas: Few-shot Learning with Retrieval Augmented Language Models

Gautier Izacard, Patrick Lewis, Maria Lomeli +7

Large language models have shown impressive few-shot results on a wide range of tasks. However, when knowledge is key for such results, as is the case for tasks such as question an…