Language Models are Few-Shot Learners

Research Publication

Examines task performance of a large autoregressive language model when supplied with examples in the prompt, alongside limitations and evaluation concerns. Authors: Brown, Tom B.; Mann, Benjamin; Ryder, Nick; Subbiah, Melanie; Kaplan, Jared; Dhariwal, Prafulla; Neelakantan, Arvind; Shyam, Pranav; Sastry, Girish; Askell, Amanda; Agarwal, Sandhini; Herbert-Voss, Ariel; Krueger, Gretchen; Henighan, Tom; Child, Rewon; Ramesh, Aditya; Ziegler, Daniel M.; Wu, Jeffrey; Winter, Clemens; Hesse, Christopher; Chen, Mark; Sigler, Eric; Litwin, Mateusz; Gray, Scott; Chess, Benjamin; Clark, Jack; Berner, Christopher; McCandlish, Sam; Radford, Alec; Sutskever, Ilya; Amodei, Dario Year: 2020 Venue: NeurIPS 2020 Research topics: Language models; in-context learning; few-shot evaluation; model scaling DOI / identifier status: 10.48550/arXiv.2005.14165 Open text / access status: https://arxiv.org/abs/2005.14165 The DOI identifies the 2020 arXiv version; the work also appeared at NeurIPS 2020. Reference: https://arxiv.org/abs/2005.14165 Curation scope: edition-aware bibliographic consistency and thematic learning associations. A publisher catalogue link or verified DOI does not by itself imply unrestricted full-text access.

Related Skills: -

Related Technologies: -

Related Careers: -

Related Sectors: -