Large Language Models and Biblical Hebrew: Limitations, pitfalls, opportunities

Researchers have been relying on computational methods to study Biblical Hebrew for a long time already. The recent improvements to and easy availability of Large Language Models (LLMs) like GPT prompt the question whether these models can be useful for our work as well. This paper tempers the expec...

Full description

Saved in:  
Bibliographic Details
Main Author: Staps, Camil (Author)
Format: Electronic Article
Language:English
Check availability: HBZ Gateway
Interlibrary Loan:Interlibrary Loan for the Fachinformationsdienste (Specialized Information Services in Germany)
Published: 2024
In: HIPHIL Novum
Year: 2024, Volume: 9, Issue: 1, Pages: 46-55
Further subjects:B Methodology
B Machine Learning
B Large Language Models
B Biblical Hebrew
Online Access: Volltext (kostenfrei)
Volltext (kostenfrei)
Description
Summary:Researchers have been relying on computational methods to study Biblical Hebrew for a long time already. The recent improvements to and easy availability of Large Language Models (LLMs) like GPT prompt the question whether these models can be useful for our work as well. This paper tempers the expectations, showing that a critical analysis of earlier work exposes fundamental issues with methods involving GPT. However, depending on the task at hand a way forward with machine learning methods is possible, once we are aware of the limitations.
ISSN:1603-6565
Contains:Enthalten in: HIPHIL Novum
Persistent identifiers:DOI: 10.7146/hn.v9i1.144177