@inproceedings{yang-etal-2025-storyllava,
title = "{S}tory{LL}a{VA}: Enhancing Visual Storytelling with Multi-Modal Large Language Models",
author = "Yang, Li and
Xiao, Zhiding and
Huang, Wenxin and
Zhong, Xian",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.266/",
pages = "3936--3951",
abstract = "The rapid development of multimodal large language models (MLLMs) has positioned visual storytelling as a crucial area in content creation. However, existing models often struggle to maintain temporal, spatial, and narrative coherence across image sequences, and they frequently lack the depth and engagement of human-authored stories. To address these challenges, we propose Story with Large Language-and-Vision Alignment (StoryLLaVA), a novel framework for enhancing visual storytelling. Our approach introduces a topic-driven narrative optimizer that improves both the training data and MLLM models by integrating image descriptions, topic generation, and GPT-4-based refinements. Furthermore, we employ a preference-based ranked story sampling method that aligns model outputs with human storytelling preferences through positive-negative pairing. These two phases of the framework differ in their training methods: the former uses supervised fine-tuning, while the latter incorporates reinforcement learning with positive and negative sample pairs. Experimental results demonstrate that StoryLLaVA outperforms current models in visual relevance, coherence, and fluency, with LLM-based evaluations confirming the generation of richer and more engaging narratives. The enhanced dataset and model will be made publicly available soon."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2025-storyllava">
<titleInfo>
<title>StoryLLaVA: Enhancing Visual Storytelling with Multi-Modal Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Li</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiding</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenxin</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xian</namePart>
<namePart type="family">Zhong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The rapid development of multimodal large language models (MLLMs) has positioned visual storytelling as a crucial area in content creation. However, existing models often struggle to maintain temporal, spatial, and narrative coherence across image sequences, and they frequently lack the depth and engagement of human-authored stories. To address these challenges, we propose Story with Large Language-and-Vision Alignment (StoryLLaVA), a novel framework for enhancing visual storytelling. Our approach introduces a topic-driven narrative optimizer that improves both the training data and MLLM models by integrating image descriptions, topic generation, and GPT-4-based refinements. Furthermore, we employ a preference-based ranked story sampling method that aligns model outputs with human storytelling preferences through positive-negative pairing. These two phases of the framework differ in their training methods: the former uses supervised fine-tuning, while the latter incorporates reinforcement learning with positive and negative sample pairs. Experimental results demonstrate that StoryLLaVA outperforms current models in visual relevance, coherence, and fluency, with LLM-based evaluations confirming the generation of richer and more engaging narratives. The enhanced dataset and model will be made publicly available soon.</abstract>
<identifier type="citekey">yang-etal-2025-storyllava</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.266/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>3936</start>
<end>3951</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T StoryLLaVA: Enhancing Visual Storytelling with Multi-Modal Large Language Models
%A Yang, Li
%A Xiao, Zhiding
%A Huang, Wenxin
%A Zhong, Xian
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F yang-etal-2025-storyllava
%X The rapid development of multimodal large language models (MLLMs) has positioned visual storytelling as a crucial area in content creation. However, existing models often struggle to maintain temporal, spatial, and narrative coherence across image sequences, and they frequently lack the depth and engagement of human-authored stories. To address these challenges, we propose Story with Large Language-and-Vision Alignment (StoryLLaVA), a novel framework for enhancing visual storytelling. Our approach introduces a topic-driven narrative optimizer that improves both the training data and MLLM models by integrating image descriptions, topic generation, and GPT-4-based refinements. Furthermore, we employ a preference-based ranked story sampling method that aligns model outputs with human storytelling preferences through positive-negative pairing. These two phases of the framework differ in their training methods: the former uses supervised fine-tuning, while the latter incorporates reinforcement learning with positive and negative sample pairs. Experimental results demonstrate that StoryLLaVA outperforms current models in visual relevance, coherence, and fluency, with LLM-based evaluations confirming the generation of richer and more engaging narratives. The enhanced dataset and model will be made publicly available soon.
%U https://aclanthology.org/2025.coling-main.266/
%P 3936-3951
Markdown (Informal)
[StoryLLaVA: Enhancing Visual Storytelling with Multi-Modal Large Language Models](https://aclanthology.org/2025.coling-main.266/) (Yang et al., COLING 2025)
ACL