@inproceedings{lucy-etal-2025-tell,
title = "Tell, Don{'}t Show: Leveraging Language Models' Abstractive Retellings to Model Literary Themes",
author = "Lucy, Li and
Griffiths, Camilla and
Levine, Sarah and
Eberhardt, Jennifer L and
Demszky, Dorottya and
Bamman, David",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.1162/",
doi = "10.18653/v1/2025.findings-acl.1162",
pages = "22585--22610",
ISBN = "979-8-89176-256-5",
abstract = "Conventional bag-of-words approaches for topic modeling, like latent Dirichlet allocation (LDA), struggle with literary text. Literature challenges lexical methods because narrative language focuses on immersive sensory details instead of abstractive description or exposition: writers are advised to *show, don{'}t tell*. We propose Retell, a simple, accessible topic modeling approach for literature. Here, we prompt resource-efficient, generative language models (LMs) to *tell* what passages *show*, thereby translating narratives' surface forms into higher-level concepts and themes. By running LDA on LMs' retellings of passages, we can obtain more precise and informative topics than by running LDA alone or by directly asking LMs to list topics. To investigate the potential of our method for cultural analytics, we compare our method{'}s outputs to expert-guided annotations in a case study on racial/cultural identity in high school English language arts books."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lucy-etal-2025-tell">
<titleInfo>
<title>Tell, Don’t Show: Leveraging Language Models’ Abstractive Retellings to Model Literary Themes</title>
</titleInfo>
<name type="personal">
<namePart type="given">Li</namePart>
<namePart type="family">Lucy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Camilla</namePart>
<namePart type="family">Griffiths</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarah</namePart>
<namePart type="family">Levine</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jennifer</namePart>
<namePart type="given">L</namePart>
<namePart type="family">Eberhardt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dorottya</namePart>
<namePart type="family">Demszky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Bamman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-256-5</identifier>
</relatedItem>
<abstract>Conventional bag-of-words approaches for topic modeling, like latent Dirichlet allocation (LDA), struggle with literary text. Literature challenges lexical methods because narrative language focuses on immersive sensory details instead of abstractive description or exposition: writers are advised to *show, don’t tell*. We propose Retell, a simple, accessible topic modeling approach for literature. Here, we prompt resource-efficient, generative language models (LMs) to *tell* what passages *show*, thereby translating narratives’ surface forms into higher-level concepts and themes. By running LDA on LMs’ retellings of passages, we can obtain more precise and informative topics than by running LDA alone or by directly asking LMs to list topics. To investigate the potential of our method for cultural analytics, we compare our method’s outputs to expert-guided annotations in a case study on racial/cultural identity in high school English language arts books.</abstract>
<identifier type="citekey">lucy-etal-2025-tell</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.1162</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.1162/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>22585</start>
<end>22610</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Tell, Don’t Show: Leveraging Language Models’ Abstractive Retellings to Model Literary Themes
%A Lucy, Li
%A Griffiths, Camilla
%A Levine, Sarah
%A Eberhardt, Jennifer L.
%A Demszky, Dorottya
%A Bamman, David
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F lucy-etal-2025-tell
%X Conventional bag-of-words approaches for topic modeling, like latent Dirichlet allocation (LDA), struggle with literary text. Literature challenges lexical methods because narrative language focuses on immersive sensory details instead of abstractive description or exposition: writers are advised to *show, don’t tell*. We propose Retell, a simple, accessible topic modeling approach for literature. Here, we prompt resource-efficient, generative language models (LMs) to *tell* what passages *show*, thereby translating narratives’ surface forms into higher-level concepts and themes. By running LDA on LMs’ retellings of passages, we can obtain more precise and informative topics than by running LDA alone or by directly asking LMs to list topics. To investigate the potential of our method for cultural analytics, we compare our method’s outputs to expert-guided annotations in a case study on racial/cultural identity in high school English language arts books.
%R 10.18653/v1/2025.findings-acl.1162
%U https://aclanthology.org/2025.findings-acl.1162/
%U https://doi.org/10.18653/v1/2025.findings-acl.1162
%P 22585-22610
Markdown (Informal)
[Tell, Don’t Show: Leveraging Language Models’ Abstractive Retellings to Model Literary Themes](https://aclanthology.org/2025.findings-acl.1162/) (Lucy et al., Findings 2025)
ACL