SCIENCE@home

Derivational morphology reveals analogical generalization in large language models

Valentin Hofmann,Leonie Weissweiler,David R. Mortensen,Hinrich Schütze,J. Pierrehumbert

Published 2025 in Proceedings of the National Academy of Sciences of the United States of America

ABSTRACT

Significance Large language models (LLMs) are a type of artificial intelligence technology that is currently being deployed in a rapidly growing range of applications. The sensitive nature of some of these applications makes it imperative that we have a precise understanding of the inner workings of LLMs. By uncovering the role of analogical mechanisms for the linguistic generalization of LLMs, our study contributes to this goal and casts a light on their impressive language skills. Furthermore, the results of our experiments have the potential to indicate pathways for further improving LLMs.

PUBLICATION RECORD

CITATION MAP

EXTRACTION MAP

CLAIMS

  • No claims are published for this paper.

CONCEPTS

  • No concepts are published for this paper.

REFERENCES

Showing 1-73 of 73 references · Page 1 of 1

CITED BY