Measuring Inductive Biases of In-Context Learning with Underspecified Demonstrations

Chenglei Si, Dan Friedman, Nitish Joshi, Shi Feng, Danqi Chen, He He

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Scopus citations

Abstract

In-context learning (ICL) is an important paradigm for adapting large language models (LLMs) to new tasks, but the generalization behavior of ICL remains poorly understood. We investigate the inductive biases of ICL from the perspective of feature bias: which feature ICL is more likely to use given a set of underspecified demonstrations in which two features are equally predictive of the labels. First, we characterize the feature biases of GPT-3 models by constructing underspecified demonstrations from a range of NLP datasets and feature combinations. We find that LLMs exhibit clear feature biases-for example, demonstrating a strong bias to predict labels according to sentiment rather than shallow lexical features, like punctuation. Second, we evaluate the effect of different interventions that are designed to impose an inductive bias in favor of a particular feature, such as adding a natural language instruction or using semantically relevant label words. We find that, while many interventions can influence the learner to prefer a particular feature, it can be difficult to overcome strong prior biases. Overall, our results provide a broader picture of the types of features that ICL may be more likely to exploit and how to impose inductive biases that are better aligned with the intended task.

Original languageEnglish (US)
Title of host publicationLong Papers
PublisherAssociation for Computational Linguistics (ACL)
Pages11289-11310
Number of pages22
ISBN (Electronic)9781959429722
StatePublished - 2023
Event61st Annual Meeting of the Association for Computational Linguistics, ACL 2023 - Toronto, Canada
Duration: Jul 9 2023Jul 14 2023

Publication series

NameProceedings of the Annual Meeting of the Association for Computational Linguistics
Volume1
ISSN (Print)0736-587X

Conference

Conference61st Annual Meeting of the Association for Computational Linguistics, ACL 2023
Country/TerritoryCanada
CityToronto
Period7/9/237/14/23

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Linguistics and Language
  • Language and Linguistics

Fingerprint

Dive into the research topics of 'Measuring Inductive Biases of In-Context Learning with Underspecified Demonstrations'. Together they form a unique fingerprint.

Cite this