Skip to main content
We gratefully acknowledge support from the Simons Foundation, member institutions, and all contributors. Donate
arXiv logo
Cornell University Logo

arXiv
Trackbacks

Trackbacks indicate external web sites that link to articles in arXiv.org. Trackbacks do not reflect the opinion of arXiv.org and may not reflect the opinions of that article's authors.

Trackback guide

By sending a trackback, you can notify arXiv.org that you have created a web page that references a paper. Popular blogging software supports trackback: you can send us a trackback about this paper by giving your software the following trackback URL:

https://arxiv.org/trackback/{arXiv_id}

Some blogging software supports trackback autodiscovery -- in this case, your software will automatically send a trackback as soon as your create a link to our abstract page. See our trackback help page for more information.

Trackbacks for 2202.12837

Paper Summary: Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?

[ ML Paper Summaries@ INVALID-URL ] trackback posted Mon, 22 Apr 2024 02:55:20 UTC

Click to view metadata for 2202.12837

[Submitted on 25 Feb 2022 (v1), last revised 20 Oct 2022 (this version, v2)]

Title:Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?

Authors:Sewon Min, Xinxi Lyu, Ari Holtzman, Mikel Artetxe, Mike Lewis, Hannaneh Hajishirzi, Luke Zettlemoyer
Abstract:
Comments: 17 pages; 12 figures. Published as a conference paper at EMNLP 2022 (long). Code available at this https URL
Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
Cite as: arXiv:2202.12837 [cs.CL]
  (or arXiv:2202.12837v2 [cs.CL] for this version)