@inproceedings{dong-2026-language,
title = "Do Language Models Use Logophoric Cues? Evidence from {M}andarin {C}hinese Long-Distance Reflexive",
author = "Dong, Yunfang",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.2135/",
pages = "43061--43072",
ISBN = "979-8-89176-395-1",
abstract = "Resolving anaphora requires integrating syntactic, semantic, and discourse information. Mandarin Chinese offers a particularly revealing case through the reflexive ziji, whose interpretation permits long-distance binding licensed by logophoric cues (i.e., cues relevant to discourse perspective). While these cues have been extensively studied in linguistic theory and psycholinguistic experiments, it remains an open question to what extent such cues are captured by computational models.We investigate this question by probing large language models' sensitivity to four logophoric cues known to license long-distance binding of ziji: predicate type, perspective marking, discourse topicality, and discourse relation. Using minimal pairs and surprisal-based measures, we assess whether models exhibit systematic biases toward non-local antecedents in logophoric contexts.Across two model families, we find that (i) models exhibit above-chance sensitivity to all four cues; (ii) lexically anchored cues are more robustly captured than discourse-level cues; and (iii) some cues generalize cross-lingually, whereas others appear to depend on language-specific training data. Taken together, these findings provide non-English evidence that large language models capture certain aspects of logophoricity, yet continue to struggle with discourse-level representations that are central to human anaphora resolution. Code and data are available at: https://github.com/yunfang-dong/mandarin-logophoricity-llm"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dong-2026-language">
<titleInfo>
<title>Do Language Models Use Logophoric Cues? Evidence from Mandarin Chinese Long-Distance Reflexive</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yunfang</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>Resolving anaphora requires integrating syntactic, semantic, and discourse information. Mandarin Chinese offers a particularly revealing case through the reflexive ziji, whose interpretation permits long-distance binding licensed by logophoric cues (i.e., cues relevant to discourse perspective). While these cues have been extensively studied in linguistic theory and psycholinguistic experiments, it remains an open question to what extent such cues are captured by computational models.We investigate this question by probing large language models’ sensitivity to four logophoric cues known to license long-distance binding of ziji: predicate type, perspective marking, discourse topicality, and discourse relation. Using minimal pairs and surprisal-based measures, we assess whether models exhibit systematic biases toward non-local antecedents in logophoric contexts.Across two model families, we find that (i) models exhibit above-chance sensitivity to all four cues; (ii) lexically anchored cues are more robustly captured than discourse-level cues; and (iii) some cues generalize cross-lingually, whereas others appear to depend on language-specific training data. Taken together, these findings provide non-English evidence that large language models capture certain aspects of logophoricity, yet continue to struggle with discourse-level representations that are central to human anaphora resolution. Code and data are available at: https://github.com/yunfang-dong/mandarin-logophoricity-llm</abstract>
<identifier type="citekey">dong-2026-language</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.2135/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>43061</start>
<end>43072</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Do Language Models Use Logophoric Cues? Evidence from Mandarin Chinese Long-Distance Reflexive
%A Dong, Yunfang
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F dong-2026-language
%X Resolving anaphora requires integrating syntactic, semantic, and discourse information. Mandarin Chinese offers a particularly revealing case through the reflexive ziji, whose interpretation permits long-distance binding licensed by logophoric cues (i.e., cues relevant to discourse perspective). While these cues have been extensively studied in linguistic theory and psycholinguistic experiments, it remains an open question to what extent such cues are captured by computational models.We investigate this question by probing large language models’ sensitivity to four logophoric cues known to license long-distance binding of ziji: predicate type, perspective marking, discourse topicality, and discourse relation. Using minimal pairs and surprisal-based measures, we assess whether models exhibit systematic biases toward non-local antecedents in logophoric contexts.Across two model families, we find that (i) models exhibit above-chance sensitivity to all four cues; (ii) lexically anchored cues are more robustly captured than discourse-level cues; and (iii) some cues generalize cross-lingually, whereas others appear to depend on language-specific training data. Taken together, these findings provide non-English evidence that large language models capture certain aspects of logophoricity, yet continue to struggle with discourse-level representations that are central to human anaphora resolution. Code and data are available at: https://github.com/yunfang-dong/mandarin-logophoricity-llm
%U https://aclanthology.org/2026.findings-acl.2135/
%P 43061-43072
Markdown (Informal)
[Do Language Models Use Logophoric Cues? Evidence from Mandarin Chinese Long-Distance Reflexive](https://aclanthology.org/2026.findings-acl.2135/) (Dong, Findings 2026)
ACL