@inproceedings{tourajmehr-etal-2025-evaluating,
title = "Evaluating the Creativity of {LLM}s in {P}ersian Literary Text Generation",
author = "Tourajmehr, Armin and
Modarres, Mohammad Reza and
Yaghoobzadeh, Yadollah",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-emnlp.796/",
pages = "14762--14774",
ISBN = "979-8-89176-335-7",
abstract = "Large language models (LLMs) have demonstrated notable creative abilities in generating literary texts, including poetry and short stories. However, prior research has primarily centered on English, with limited exploration of non-English literary traditions and without standardized methods for assessing creativity. In this paper, we evaluate the capacity of LLMs to generate Persian literary text enriched with culturally relevant expressions. We build a dataset of user-generated Persian literary spanning 20 diverse topics and assess model outputs along four creativity dimensions{---}originality, fluency, flexibility, and elaboration{---}by adapting the Torrance Tests of Creative Thinking. To reduce evaluation costs, we adopt an LLM as a judge for automated scoring and validate its reliability against human judgments using intraclass correlation coefficients, observing strong agreement. In addition, we analyze the models' ability to understand and employ four core literary devices: simile, metaphor, hyperbole, and antithesis. Our results highlight both the strengths and limitations of LLMs in Persian literary text generation, underscoring the need for further refinement."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tourajmehr-etal-2025-evaluating">
<titleInfo>
<title>Evaluating the Creativity of LLMs in Persian Literary Text Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Armin</namePart>
<namePart type="family">Tourajmehr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Reza</namePart>
<namePart type="family">Modarres</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yadollah</namePart>
<namePart type="family">Yaghoobzadeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-335-7</identifier>
</relatedItem>
<abstract>Large language models (LLMs) have demonstrated notable creative abilities in generating literary texts, including poetry and short stories. However, prior research has primarily centered on English, with limited exploration of non-English literary traditions and without standardized methods for assessing creativity. In this paper, we evaluate the capacity of LLMs to generate Persian literary text enriched with culturally relevant expressions. We build a dataset of user-generated Persian literary spanning 20 diverse topics and assess model outputs along four creativity dimensions—originality, fluency, flexibility, and elaboration—by adapting the Torrance Tests of Creative Thinking. To reduce evaluation costs, we adopt an LLM as a judge for automated scoring and validate its reliability against human judgments using intraclass correlation coefficients, observing strong agreement. In addition, we analyze the models’ ability to understand and employ four core literary devices: simile, metaphor, hyperbole, and antithesis. Our results highlight both the strengths and limitations of LLMs in Persian literary text generation, underscoring the need for further refinement.</abstract>
<identifier type="citekey">tourajmehr-etal-2025-evaluating</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.796/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>14762</start>
<end>14774</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating the Creativity of LLMs in Persian Literary Text Generation
%A Tourajmehr, Armin
%A Modarres, Mohammad Reza
%A Yaghoobzadeh, Yadollah
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F tourajmehr-etal-2025-evaluating
%X Large language models (LLMs) have demonstrated notable creative abilities in generating literary texts, including poetry and short stories. However, prior research has primarily centered on English, with limited exploration of non-English literary traditions and without standardized methods for assessing creativity. In this paper, we evaluate the capacity of LLMs to generate Persian literary text enriched with culturally relevant expressions. We build a dataset of user-generated Persian literary spanning 20 diverse topics and assess model outputs along four creativity dimensions—originality, fluency, flexibility, and elaboration—by adapting the Torrance Tests of Creative Thinking. To reduce evaluation costs, we adopt an LLM as a judge for automated scoring and validate its reliability against human judgments using intraclass correlation coefficients, observing strong agreement. In addition, we analyze the models’ ability to understand and employ four core literary devices: simile, metaphor, hyperbole, and antithesis. Our results highlight both the strengths and limitations of LLMs in Persian literary text generation, underscoring the need for further refinement.
%U https://aclanthology.org/2025.findings-emnlp.796/
%P 14762-14774
Markdown (Informal)
[Evaluating the Creativity of LLMs in Persian Literary Text Generation](https://aclanthology.org/2025.findings-emnlp.796/) (Tourajmehr et al., Findings 2025)
ACL