@inproceedings{zhang-etal-2026-diting,
title = "{DITING}: Evaluating Sentence-Level Cultural Meaning in Web Novel Translation",
author = "Zhang, Enze and
Wang, Jiaying and
Xiao, Mengxi and
Liu, Jifei and
Hu, Zhiwei and
Kuang, Ziyan and
Dong, Rui and
Dong, Youzhong and
Kabir, Mohsinul and
Gutierrez Basulto, Victor and
Peng, Min and
Xie, Qianqian and
Ananiadou, Sophia",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.1959/",
pages = "44605--44638",
ISBN = "979-8-89176-459-0",
abstract = "Large language models are increasingly regarded as strong translators, yet it remains unclear what their success establishes beyond overall translation quality. This question is especially consequential in Chinese web novel translation, where sentence-level cultural meaning shapes tone, characterization, and reader experience. Existing evaluation provides only indirect evidence, as benchmarks emphasize overall quality and available metrics do not explicitly assess the cultural and pragmatic phenomena underlying reader experience. We introduce DITING (a mythological creature known for discerning truth), the first comprehensive evaluation framework for this problem, supported by an expert-annotated benchmark of over 18K Chinese-English sentence pairs, a reasoning-driven multi-agent evaluator, AgentEval, and a 1,440-pair meta-evaluation benchmark, MetricAlign. AgentEval achieves the strongest correlation with human judgments among eight representative automatic metrics. Applying DITING to 14 translation systems shows that current progress is selective rather than general: frontier LLMs lead overall, but their gains concentrate in a subset of dimensions, while zero-pronoun resolution remains the clearest bottleneck. Overall, our results show that aggregate rankings substantially overstate how broadly sentence-level cultural meaning has been solved in web novel translation. All the code and data in https://github.com/whunextgen/DITING."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2026-diting">
<titleInfo>
<title>DITING: Evaluating Sentence-Level Cultural Meaning in Web Novel Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Enze</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaying</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mengxi</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jifei</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiwei</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ziyan</namePart>
<namePart type="family">Kuang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Youzhong</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohsinul</namePart>
<namePart type="family">Kabir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Victor</namePart>
<namePart type="family">Gutierrez Basulto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qianqian</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</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</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</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">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Large language models are increasingly regarded as strong translators, yet it remains unclear what their success establishes beyond overall translation quality. This question is especially consequential in Chinese web novel translation, where sentence-level cultural meaning shapes tone, characterization, and reader experience. Existing evaluation provides only indirect evidence, as benchmarks emphasize overall quality and available metrics do not explicitly assess the cultural and pragmatic phenomena underlying reader experience. We introduce DITING (a mythological creature known for discerning truth), the first comprehensive evaluation framework for this problem, supported by an expert-annotated benchmark of over 18K Chinese-English sentence pairs, a reasoning-driven multi-agent evaluator, AgentEval, and a 1,440-pair meta-evaluation benchmark, MetricAlign. AgentEval achieves the strongest correlation with human judgments among eight representative automatic metrics. Applying DITING to 14 translation systems shows that current progress is selective rather than general: frontier LLMs lead overall, but their gains concentrate in a subset of dimensions, while zero-pronoun resolution remains the clearest bottleneck. Overall, our results show that aggregate rankings substantially overstate how broadly sentence-level cultural meaning has been solved in web novel translation. All the code and data in https://github.com/whunextgen/DITING.</abstract>
<identifier type="citekey">zhang-etal-2026-diting</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.1959/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>44605</start>
<end>44638</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DITING: Evaluating Sentence-Level Cultural Meaning in Web Novel Translation
%A Zhang, Enze
%A Wang, Jiaying
%A Xiao, Mengxi
%A Liu, Jifei
%A Hu, Zhiwei
%A Kuang, Ziyan
%A Dong, Rui
%A Dong, Youzhong
%A Kabir, Mohsinul
%A Gutierrez Basulto, Victor
%A Peng, Min
%A Xie, Qianqian
%A Ananiadou, Sophia
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F zhang-etal-2026-diting
%X Large language models are increasingly regarded as strong translators, yet it remains unclear what their success establishes beyond overall translation quality. This question is especially consequential in Chinese web novel translation, where sentence-level cultural meaning shapes tone, characterization, and reader experience. Existing evaluation provides only indirect evidence, as benchmarks emphasize overall quality and available metrics do not explicitly assess the cultural and pragmatic phenomena underlying reader experience. We introduce DITING (a mythological creature known for discerning truth), the first comprehensive evaluation framework for this problem, supported by an expert-annotated benchmark of over 18K Chinese-English sentence pairs, a reasoning-driven multi-agent evaluator, AgentEval, and a 1,440-pair meta-evaluation benchmark, MetricAlign. AgentEval achieves the strongest correlation with human judgments among eight representative automatic metrics. Applying DITING to 14 translation systems shows that current progress is selective rather than general: frontier LLMs lead overall, but their gains concentrate in a subset of dimensions, while zero-pronoun resolution remains the clearest bottleneck. Overall, our results show that aggregate rankings substantially overstate how broadly sentence-level cultural meaning has been solved in web novel translation. All the code and data in https://github.com/whunextgen/DITING.
%U https://aclanthology.org/2026.emnlp-main.1959/
%P 44605-44638
Markdown (Informal)
[DITING: Evaluating Sentence-Level Cultural Meaning in Web Novel Translation](https://aclanthology.org/2026.emnlp-main.1959/) (Zhang et al., EMNLP 2026)
ACL
- Enze Zhang, Jiaying Wang, Mengxi Xiao, Jifei Liu, Zhiwei Hu, Ziyan Kuang, Rui Dong, Youzhong Dong, Mohsinul Kabir, Victor Gutierrez Basulto, Min Peng, Qianqian Xie, and Sophia Ananiadou. 2026. DITING: Evaluating Sentence-Level Cultural Meaning in Web Novel Translation. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 44605–44638, Budapest, Hungary. Association for Computational Linguistics.