Limitations of and lessons from the learning of large language models

  • It is argued that the Curry-Howard correspondence for classical logic implies limitations for logical reasoning that can be learned and performed by large language models. The correspondence establishes an isomorphism between proofs in logic and programs in functional typed lambda calculus. While intuitionistic logic maps to a version of lambda calculus that can be carried out in a local way, i.e., considering local parts of the code in isolation, the version of lambda calculus that corresponds to classical logic requires non-local relations – and this non-locality cannot be learned by large language models due to their restriction to investigate a relative short sequence of tokens. A possible way to go beyond this limitation is sketched as well. Implications for other areas are investigated as well.

Download full text files

Export metadata

Statistics

Number of document requests

Additional Services

Share in Twitter Search Google Scholar
Metadaten
Author:Reinhard OldenburgORCiDGND
URN:urn:nbn:de:bvb:384-opus4-1107659
Frontdoor URLhttps://opus.bibliothek.uni-augsburg.de/opus4/110765
ISSN:2632-3834OPAC
Parent Title (English):Qeios
Publisher:Qeios
Type:Article
Language:English
Year of first Publication:2023
Publishing Institution:Universität Augsburg
Release Date:2024/01/15
Tag:Process Chemistry and Technology; Economic Geology; Fuel Technology
First Page:9FH6AD
DOI:https://doi.org/10.32388/9fh6ad
Institutes:Mathematisch-Naturwissenschaftlich-Technische Fakultät
Mathematisch-Naturwissenschaftlich-Technische Fakultät / Institut für Mathematik
Mathematisch-Naturwissenschaftlich-Technische Fakultät / Institut für Mathematik / Lehrstuhl für Didaktik der Mathematik
Dewey Decimal Classification:5 Naturwissenschaften und Mathematik / 51 Mathematik / 510 Mathematik
Licence (German):CC-BY 4.0: Creative Commons: Namensnennung (mit Print on Demand)