@inproceedings{wang-etal-2026-d2gs,
title = "{D}2{GS}: A Data-Centric Framework for {LLM}-based Creative Game Script Generation",
author = "Wang, Jiali and
Huang, Junbao and
Chen, Minghao",
editor = "Atanasova, Pepa and
Haffari, Gholamreza and
Wang, Minghan",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-industry.107/",
pages = "1840--1853",
ISBN = "979-8-89176-460-6",
abstract = "Although Large Language Models (LLMs) offer significant advantages for creative tasks like game narrative design, their application remains largely confined to academic exploration. Existing methods often fail to integrate with specific game assets, production constraints, and iterative workflows essential for industrial development, limiting real deployment in professional studios. To bridge this gap, we present D2GS, a data-centric framework for LLM-based game script generation designed for industry. D2GS supports narrative designers end-to-end, from ideation to engine-ready scripts. It grounds creation in multi-source, game-specific data and mimics human iterative refinement. The framework includes four modules: (1) knowledge augmentation for multi-source data preparation; (2) logline and plot outline generation with a critic-feedback revision loop; (3) character and world enrichment using role-assigned LLM agents to simulate interactions; and (4) script rephrasing to ensure game-engine compatibility. Experiments show D2GS outperforms strong baselines in coherence, relevance, creativity, and overall writing quality, while staying faithful to predefined settings and assets. Industrial-scale validation further confirms its practicality for real-world narrative design pipelines."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2026-d2gs">
<titleInfo>
<title>D2GS: A Data-Centric Framework for LLM-based Creative Game Script Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiali</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junbao</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minghao</namePart>
<namePart type="family">Chen</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 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pepa</namePart>
<namePart type="family">Atanasova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gholamreza</namePart>
<namePart type="family">Haffari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minghan</namePart>
<namePart type="family">Wang</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">979-8-89176-460-6</identifier>
</relatedItem>
<abstract>Although Large Language Models (LLMs) offer significant advantages for creative tasks like game narrative design, their application remains largely confined to academic exploration. Existing methods often fail to integrate with specific game assets, production constraints, and iterative workflows essential for industrial development, limiting real deployment in professional studios. To bridge this gap, we present D2GS, a data-centric framework for LLM-based game script generation designed for industry. D2GS supports narrative designers end-to-end, from ideation to engine-ready scripts. It grounds creation in multi-source, game-specific data and mimics human iterative refinement. The framework includes four modules: (1) knowledge augmentation for multi-source data preparation; (2) logline and plot outline generation with a critic-feedback revision loop; (3) character and world enrichment using role-assigned LLM agents to simulate interactions; and (4) script rephrasing to ensure game-engine compatibility. Experiments show D2GS outperforms strong baselines in coherence, relevance, creativity, and overall writing quality, while staying faithful to predefined settings and assets. Industrial-scale validation further confirms its practicality for real-world narrative design pipelines.</abstract>
<identifier type="citekey">wang-etal-2026-d2gs</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-industry.107/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1840</start>
<end>1853</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T D2GS: A Data-Centric Framework for LLM-based Creative Game Script Generation
%A Wang, Jiali
%A Huang, Junbao
%A Chen, Minghao
%Y Atanasova, Pepa
%Y Haffari, Gholamreza
%Y Wang, Minghan
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-460-6
%F wang-etal-2026-d2gs
%X Although Large Language Models (LLMs) offer significant advantages for creative tasks like game narrative design, their application remains largely confined to academic exploration. Existing methods often fail to integrate with specific game assets, production constraints, and iterative workflows essential for industrial development, limiting real deployment in professional studios. To bridge this gap, we present D2GS, a data-centric framework for LLM-based game script generation designed for industry. D2GS supports narrative designers end-to-end, from ideation to engine-ready scripts. It grounds creation in multi-source, game-specific data and mimics human iterative refinement. The framework includes four modules: (1) knowledge augmentation for multi-source data preparation; (2) logline and plot outline generation with a critic-feedback revision loop; (3) character and world enrichment using role-assigned LLM agents to simulate interactions; and (4) script rephrasing to ensure game-engine compatibility. Experiments show D2GS outperforms strong baselines in coherence, relevance, creativity, and overall writing quality, while staying faithful to predefined settings and assets. Industrial-scale validation further confirms its practicality for real-world narrative design pipelines.
%U https://aclanthology.org/2026.emnlp-industry.107/
%P 1840-1853
Markdown (Informal)
[D2GS: A Data-Centric Framework for LLM-based Creative Game Script Generation](https://aclanthology.org/2026.emnlp-industry.107/) (Wang et al., EMNLP 2026)
ACL