Bits of grass: does GPT already know how to write like Whitman?

Sawicki, Piotr, Grzes, Marek, Goes, Fabricio, Brown, Dan, Peeperkorn, Max, Khatun, Aisha (2023) Bits of grass: does GPT already know how to write like Whitman? In: Proceedings of the 14th International Conference for Computational Creativity. . (In press) (KAR id:101550)

PDF Author's Accepted Manuscript Language: English
Download this file (PDF/175kB)	Preview
Request a format suitable for use with assistive technology e.g. a screenreader

Abstract

This study examines the ability of GPT-3.5, GPT-3.5-turbo (ChatGPT) and GPT-4 models to generate poems in the style of specific authors using zero-shot and many-shot prompts (which use the maximum context length of 8192 tokens). We assess the performance of models that are not fine-tuned for generating poetry in the style of specific authors, via automated evaluation. Our findings indicate that without finetuning, even when provided with the maximum number of 17 poem examples (8192 tokens) in the prompt, these models do not generate poetry in the desired style.

Item Type:	Conference or workshop item (Poster)
Uncontrolled keywords:	GPT; NLP; poetry; fine-tuning; LLMs
Subjects:	Q Science > Q Science (General) > Q335 Artificial intelligence
Divisions:	Divisions > Division of Computing, Engineering and Mathematical Sciences > School of Computing
Funders:	University of Kent (https://ror.org/00xkeyj56)
Depositing User:	Piotr Sawicki
Date Deposited:	05 Jun 2023 17:10 UTC
Last Modified:	09 Jun 2023 13:08 UTC
Resource URI:	https://kar.kent.ac.uk/id/eprint/101550 (The current URI for this page, for reference purposes)

University of Kent Author Information

Sawicki, Piotr.

Creator's ORCID:
CReDIT Contributor Roles:

Grzes, Marek.

Creator's ORCID:	https://orcid.org/0000-0003-4901-1539
CReDIT Contributor Roles:

Peeperkorn, Max.

Creator's ORCID:	https://orcid.org/0000-0001-9058-0886
CReDIT Contributor Roles:

Depositors only (login required):

Download Statistics

Total unique views for this document in KAR since July 2020. For more details click on the image.