@inproceedings{yang-etal-2026-evaluating,
title = "Evaluating Coreference Consistency in {C}hinese-to-{E}nglish Dialogue Translation",
author = "Yang, Xu and
Gong, Zhengxian and
Li, Junhui and
Yang, Jinlong and
Zhang, Min and
Tao, Shimin and
Wei, Daimeng",
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.2056/",
pages = "46817--46833",
ISBN = "979-8-89176-459-0",
abstract = "Coreference consistency is essential for preserving discourse coherence in dialogue translation, yet it remains underexplored in the context of large language models (LLMs). In this paper, we present a comprehensive study of coreference preservation in Chinese-to-English dialogue translation. We construct a new dataset based on the RiSAWOZ corpus, annotated with source-side zero pronouns and coreference chains. Translations are obtained from a diverse set of LLMs of varying sizes. To evaluate whether coreference relations are maintained, we propose the Coreference Consistency Score (CCS), which quantifies the extent to which translated mentions preserve original coreferential chains. We further introduce an LLM-as-Judge protocol for assessing the faithfulness of translated mentions. Our results reveal that, despite producing fluent translations, many LLMs, including both small and large models, struggle to maintain cross-lingual coreference, highlighting the need for more discourse-aware dialogue translation models. All code and data will be released."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2026-evaluating">
<titleInfo>
<title>Evaluating Coreference Consistency in Chinese-to-English Dialogue Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xu</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhengxian</namePart>
<namePart type="family">Gong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junhui</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinlong</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shimin</namePart>
<namePart type="family">Tao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daimeng</namePart>
<namePart type="family">Wei</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>Coreference consistency is essential for preserving discourse coherence in dialogue translation, yet it remains underexplored in the context of large language models (LLMs). In this paper, we present a comprehensive study of coreference preservation in Chinese-to-English dialogue translation. We construct a new dataset based on the RiSAWOZ corpus, annotated with source-side zero pronouns and coreference chains. Translations are obtained from a diverse set of LLMs of varying sizes. To evaluate whether coreference relations are maintained, we propose the Coreference Consistency Score (CCS), which quantifies the extent to which translated mentions preserve original coreferential chains. We further introduce an LLM-as-Judge protocol for assessing the faithfulness of translated mentions. Our results reveal that, despite producing fluent translations, many LLMs, including both small and large models, struggle to maintain cross-lingual coreference, highlighting the need for more discourse-aware dialogue translation models. All code and data will be released.</abstract>
<identifier type="citekey">yang-etal-2026-evaluating</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.2056/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>46817</start>
<end>46833</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating Coreference Consistency in Chinese-to-English Dialogue Translation
%A Yang, Xu
%A Gong, Zhengxian
%A Li, Junhui
%A Yang, Jinlong
%A Zhang, Min
%A Tao, Shimin
%A Wei, Daimeng
%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 yang-etal-2026-evaluating
%X Coreference consistency is essential for preserving discourse coherence in dialogue translation, yet it remains underexplored in the context of large language models (LLMs). In this paper, we present a comprehensive study of coreference preservation in Chinese-to-English dialogue translation. We construct a new dataset based on the RiSAWOZ corpus, annotated with source-side zero pronouns and coreference chains. Translations are obtained from a diverse set of LLMs of varying sizes. To evaluate whether coreference relations are maintained, we propose the Coreference Consistency Score (CCS), which quantifies the extent to which translated mentions preserve original coreferential chains. We further introduce an LLM-as-Judge protocol for assessing the faithfulness of translated mentions. Our results reveal that, despite producing fluent translations, many LLMs, including both small and large models, struggle to maintain cross-lingual coreference, highlighting the need for more discourse-aware dialogue translation models. All code and data will be released.
%U https://aclanthology.org/2026.emnlp-main.2056/
%P 46817-46833
Markdown (Informal)
[Evaluating Coreference Consistency in Chinese-to-English Dialogue Translation](https://aclanthology.org/2026.emnlp-main.2056/) (Yang et al., EMNLP 2026)
ACL