@inproceedings{perdijk-etal-2026-stories,
title = "Stories for the Win: Creating and Evaluating a Synthetic {D}utch Children{'}s Storytelling Dataset",
author = "Perdijk, Sabijn and
Wijnholds, Gijs and
Verberne, Suzan and
van Duijn, Max J.",
editor = "Choshen, Leshem and
Cotterell, Ryan and
Gul, Mustafa Omer and
Jumelet, Jaap and
Linzen, Tal and
Mueller, Aaron and
Salhan, Suchir and
Shah, Raj Sanjay and
Warstadt, Alex and
Wilcox, Ethan Gotlieb",
booktitle = "Proceedings of the Second {B}aby{LM} Workshop",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.babylm-main.36/",
pages = "459--478",
ISBN = "979-8-89176-475-0",
abstract = "Stories have been shown to be potentially valuable for language model pretraining because their semantics are largely self-grounded. Existing human storytelling datasets are relatively small, and existing synthetic datasets lack realism. Here we describe the guided synthesis of a story corpus that is both large and realistic. We evaluate a set of metrics for measuring the quality of individual stories, including coherence, surprise, complexity, as well for quality of the dataset as a whole. Using the metrics we extensively evaluate multiple prompting approaches and three small models (3-8B). Based on the results, we steer dataset generation to yield a high-quality `synthetic twin' of a Dutch children{'}s storytelling collection, similar in terms of lexical and semantic diversity, but much larger, which we call *Stories for the Win* (StoriesFTW). We validate our metrics and evaluate samples from our corpus with crowd, expert, and LLM judgements."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="perdijk-etal-2026-stories">
<titleInfo>
<title>Stories for the Win: Creating and Evaluating a Synthetic Dutch Children’s Storytelling Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sabijn</namePart>
<namePart type="family">Perdijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gijs</namePart>
<namePart type="family">Wijnholds</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Suzan</namePart>
<namePart type="family">Verberne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Max</namePart>
<namePart type="given">J</namePart>
<namePart type="family">van Duijn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second BabyLM Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Leshem</namePart>
<namePart type="family">Choshen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mustafa</namePart>
<namePart type="given">Omer</namePart>
<namePart type="family">Gul</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaap</namePart>
<namePart type="family">Jumelet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tal</namePart>
<namePart type="family">Linzen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aaron</namePart>
<namePart type="family">Mueller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Suchir</namePart>
<namePart type="family">Salhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raj</namePart>
<namePart type="given">Sanjay</namePart>
<namePart type="family">Shah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Warstadt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ethan</namePart>
<namePart type="given">Gotlieb</namePart>
<namePart type="family">Wilcox</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-475-0</identifier>
</relatedItem>
<abstract>Stories have been shown to be potentially valuable for language model pretraining because their semantics are largely self-grounded. Existing human storytelling datasets are relatively small, and existing synthetic datasets lack realism. Here we describe the guided synthesis of a story corpus that is both large and realistic. We evaluate a set of metrics for measuring the quality of individual stories, including coherence, surprise, complexity, as well for quality of the dataset as a whole. Using the metrics we extensively evaluate multiple prompting approaches and three small models (3-8B). Based on the results, we steer dataset generation to yield a high-quality ‘synthetic twin’ of a Dutch children’s storytelling collection, similar in terms of lexical and semantic diversity, but much larger, which we call *Stories for the Win* (StoriesFTW). We validate our metrics and evaluate samples from our corpus with crowd, expert, and LLM judgements.</abstract>
<identifier type="citekey">perdijk-etal-2026-stories</identifier>
<location>
<url>https://aclanthology.org/2026.babylm-main.36/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>459</start>
<end>478</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Stories for the Win: Creating and Evaluating a Synthetic Dutch Children’s Storytelling Dataset
%A Perdijk, Sabijn
%A Wijnholds, Gijs
%A Verberne, Suzan
%A van Duijn, Max J.
%Y Choshen, Leshem
%Y Cotterell, Ryan
%Y Gul, Mustafa Omer
%Y Jumelet, Jaap
%Y Linzen, Tal
%Y Mueller, Aaron
%Y Salhan, Suchir
%Y Shah, Raj Sanjay
%Y Warstadt, Alex
%Y Wilcox, Ethan Gotlieb
%S Proceedings of the Second BabyLM Workshop
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-475-0
%F perdijk-etal-2026-stories
%X Stories have been shown to be potentially valuable for language model pretraining because their semantics are largely self-grounded. Existing human storytelling datasets are relatively small, and existing synthetic datasets lack realism. Here we describe the guided synthesis of a story corpus that is both large and realistic. We evaluate a set of metrics for measuring the quality of individual stories, including coherence, surprise, complexity, as well for quality of the dataset as a whole. Using the metrics we extensively evaluate multiple prompting approaches and three small models (3-8B). Based on the results, we steer dataset generation to yield a high-quality ‘synthetic twin’ of a Dutch children’s storytelling collection, similar in terms of lexical and semantic diversity, but much larger, which we call *Stories for the Win* (StoriesFTW). We validate our metrics and evaluate samples from our corpus with crowd, expert, and LLM judgements.
%U https://aclanthology.org/2026.babylm-main.36/
%P 459-478
Markdown (Informal)
[Stories for the Win: Creating and Evaluating a Synthetic Dutch Children’s Storytelling Dataset](https://aclanthology.org/2026.babylm-main.36/) (Perdijk et al., BabyLM 2026)
ACL