@inproceedings{kazi-etal-2026-adaptation,
title = "Adaptation, Not Translation: An Architecture and Evaluation Framework for Long-Form Cross-Cultural Story Localization",
author = "Kazi, Taaha and
Kanade, Aditya Sanjiv and
Yang, Ivory and
Saifullah, Mohammad and
Sharma, Vasu and
Pant, Bhavesh and
Bhatia, Kunal and
Prakash, Abhinav and
Rahman, Abdur and
Agarwal, Varun and
Jain, Sarjita and
Pavate, Viveca and
Maithul, Nishita",
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.122/",
pages = "2093--2114",
ISBN = "979-8-89176-460-6",
abstract = "Translating a story renders its words into a new language; adapting it transposes its world into a new culture. Large Language Models (LLMs) translate and adapt individual passages effectively, but long-form novels spanning $\sim$100 chapters suffer model failures. We formalize long-form cross-cultural story adaptation as a generation task parameterized by source and target language-culture pairs, with three structural axes: A1 identity coherence across narrative arc, A2 cultural-system alignment within scenes, and A3 dependency-chain integrity among related entities. This is addressed through a five-stage agentic adaptation framework comprising entity registry, target-culture plan, dependency-aware batched localization, validation and rewrite. Evaluation is conducted through ablations across three language-culture pairs and two model families; the proposed system outperforms across all three axes, reducing identity errors by 65{\%}, dependency errors by 64{\%}, and cultural misalignment errors by 27{\%} against competitive baselines. Further validation through a production A/B test on a commercial storytelling platform demonstrates listener retention comparable to that for human-adapted content, reflecting viability of the framework."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kazi-etal-2026-adaptation">
<titleInfo>
<title>Adaptation, Not Translation: An Architecture and Evaluation Framework for Long-Form Cross-Cultural Story Localization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Taaha</namePart>
<namePart type="family">Kazi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aditya</namePart>
<namePart type="given">Sanjiv</namePart>
<namePart type="family">Kanade</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivory</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="family">Saifullah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vasu</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bhavesh</namePart>
<namePart type="family">Pant</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kunal</namePart>
<namePart type="family">Bhatia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhinav</namePart>
<namePart type="family">Prakash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdur</namePart>
<namePart type="family">Rahman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Varun</namePart>
<namePart type="family">Agarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarjita</namePart>
<namePart type="family">Jain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viveca</namePart>
<namePart type="family">Pavate</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nishita</namePart>
<namePart type="family">Maithul</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>Translating a story renders its words into a new language; adapting it transposes its world into a new culture. Large Language Models (LLMs) translate and adapt individual passages effectively, but long-form novels spanning \sim100 chapters suffer model failures. We formalize long-form cross-cultural story adaptation as a generation task parameterized by source and target language-culture pairs, with three structural axes: A1 identity coherence across narrative arc, A2 cultural-system alignment within scenes, and A3 dependency-chain integrity among related entities. This is addressed through a five-stage agentic adaptation framework comprising entity registry, target-culture plan, dependency-aware batched localization, validation and rewrite. Evaluation is conducted through ablations across three language-culture pairs and two model families; the proposed system outperforms across all three axes, reducing identity errors by 65%, dependency errors by 64%, and cultural misalignment errors by 27% against competitive baselines. Further validation through a production A/B test on a commercial storytelling platform demonstrates listener retention comparable to that for human-adapted content, reflecting viability of the framework.</abstract>
<identifier type="citekey">kazi-etal-2026-adaptation</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-industry.122/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>2093</start>
<end>2114</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Adaptation, Not Translation: An Architecture and Evaluation Framework for Long-Form Cross-Cultural Story Localization
%A Kazi, Taaha
%A Kanade, Aditya Sanjiv
%A Yang, Ivory
%A Saifullah, Mohammad
%A Sharma, Vasu
%A Pant, Bhavesh
%A Bhatia, Kunal
%A Prakash, Abhinav
%A Rahman, Abdur
%A Agarwal, Varun
%A Jain, Sarjita
%A Pavate, Viveca
%A Maithul, Nishita
%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 kazi-etal-2026-adaptation
%X Translating a story renders its words into a new language; adapting it transposes its world into a new culture. Large Language Models (LLMs) translate and adapt individual passages effectively, but long-form novels spanning \sim100 chapters suffer model failures. We formalize long-form cross-cultural story adaptation as a generation task parameterized by source and target language-culture pairs, with three structural axes: A1 identity coherence across narrative arc, A2 cultural-system alignment within scenes, and A3 dependency-chain integrity among related entities. This is addressed through a five-stage agentic adaptation framework comprising entity registry, target-culture plan, dependency-aware batched localization, validation and rewrite. Evaluation is conducted through ablations across three language-culture pairs and two model families; the proposed system outperforms across all three axes, reducing identity errors by 65%, dependency errors by 64%, and cultural misalignment errors by 27% against competitive baselines. Further validation through a production A/B test on a commercial storytelling platform demonstrates listener retention comparable to that for human-adapted content, reflecting viability of the framework.
%U https://aclanthology.org/2026.emnlp-industry.122/
%P 2093-2114
Markdown (Informal)
[Adaptation, Not Translation: An Architecture and Evaluation Framework for Long-Form Cross-Cultural Story Localization](https://aclanthology.org/2026.emnlp-industry.122/) (Kazi et al., EMNLP 2026)
ACL
- Taaha Kazi, Aditya Sanjiv Kanade, Ivory Yang, Mohammad Saifullah, Vasu Sharma, Bhavesh Pant, Kunal Bhatia, Abhinav Prakash, Abdur Rahman, Varun Agarwal, Sarjita Jain, Viveca Pavate, and Nishita Maithul. 2026. Adaptation, Not Translation: An Architecture and Evaluation Framework for Long-Form Cross-Cultural Story Localization. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 2093–2114, Budapest, Hungary. Association for Computational Linguistics.