Diverse Demonstrations Improve In-context Compositional Generalization

Itay Levy, Ben Bogin, Jonathan Berant

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


In-context learning has shown great success in i.i.d semantic parsing splits, where the training and test sets are drawn from the same distribution. In this setup, models are typically prompted with demonstrations that are similar to the input utterance. However, in the setup of compositional generalization, where models are tested on outputs with structures that are absent from the training set, selecting similar demonstrations is insufficient, as often no example will be similar enough to the input. In this work, we propose a method to select diverse demonstrations that aims to collectively cover all of the structures required in the output program, in order to encourage the model to generalize to new structures from these demonstrations. We empirically show that combining diverse demonstrations with in-context learning substantially improves performance across three compositional generalization semantic parsing datasets in the pure in-context learning setup and when combined with finetuning.

Original languageEnglish
Title of host publicationLong Papers
PublisherAssociation for Computational Linguistics (ACL)
Number of pages22
ISBN (Electronic)9781959429722
StatePublished - 2023
Event61st Annual Meeting of the Association for Computational Linguistics, ACL 2023 - Toronto, Canada
Duration: 9 Jul 202314 Jul 2023

Publication series

NameProceedings of the Annual Meeting of the Association for Computational Linguistics
ISSN (Print)0736-587X


Conference61st Annual Meeting of the Association for Computational Linguistics, ACL 2023


Dive into the research topics of 'Diverse Demonstrations Improve In-context Compositional Generalization'. Together they form a unique fingerprint.

Cite this