@inproceedings{safakar-pado-2026-testing,
title = "Testing Language Model Sensitivity to Object-Anaphoric Accessibility: {P}ersian ye(k) and {E}nglish indefinite this",
author = "Safakar, Nikta Yekrang and
Pad{\'o}, Sebastian",
editor = "Adelani, David Ifeoluwa and
Alabi, Jesujoba and
Arnett, Catherine and
Chang, Tyler and
Downey, C.M. and
Goldman, Omer and
Li, Senyu and
Miranda, Lester James Validad and
Qi, Jirui and
Stap, David and
Winata, Genta Indra and
Zhang, Xinyu Crystina",
booktitle = "Proceedings of the 6th Workshop on Multilingual Representation Learning ({MRL} 2026)",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.mrl-1.14/",
pages = "183--195",
ISBN = "979-8-89176-469-9",
abstract = "How accessible a discourse referent is for later mention depends on how it is introduced: indefinite marking can make an entity more accessible for anaphora. This dimension is computationally understudied. We ask whether language models are sensitive to this discourse function as encoded by Persian ye(k). Linguistic theory for Persian predicts that ye(k)-marked objects support anaphoric uptake more readily than bare objects. Comparing a bare object against a minimally different ye(k)-marked object, we find that both encoder- and decoder-based models assign higher scores to object-anaphoric uptake material after ye(k) contexts. The effect is reliable at the object-anaphoric NP and, in six of seven decoders, exceeds both subject-span and neutral-continuation controls, but is weaker and more model-dependent over the whole continuation. We find a parallel directional effect for an English indefinite-this contrast, showing that a comparable downstream anaphoric-uptake pattern is observable with a different language-specific cue. As a secondary finding, we show that the scoring unit (only the anaphoric uptake site vs. the whole continuation) matters, and that the local site provides a clearer signal. We will release the Persian and English stimulus sets, item-level scores, and reproduction scripts upon publication."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="safakar-pado-2026-testing">
<titleInfo>
<title>Testing Language Model Sensitivity to Object-Anaphoric Accessibility: Persian ye(k) and English indefinite this</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikta</namePart>
<namePart type="given">Yekrang</namePart>
<namePart type="family">Safakar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Padó</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 6th Workshop on Multilingual Representation Learning (MRL 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="given">Ifeoluwa</namePart>
<namePart type="family">Adelani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jesujoba</namePart>
<namePart type="family">Alabi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Catherine</namePart>
<namePart type="family">Arnett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tyler</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">C</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Downey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omer</namePart>
<namePart type="family">Goldman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Senyu</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lester</namePart>
<namePart type="given">James</namePart>
<namePart type="given">Validad</namePart>
<namePart type="family">Miranda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jirui</namePart>
<namePart type="family">Qi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Stap</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Genta</namePart>
<namePart type="given">Indra</namePart>
<namePart type="family">Winata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinyu</namePart>
<namePart type="given">Crystina</namePart>
<namePart type="family">Zhang</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">979-8-89176-469-9</identifier>
</relatedItem>
<abstract>How accessible a discourse referent is for later mention depends on how it is introduced: indefinite marking can make an entity more accessible for anaphora. This dimension is computationally understudied. We ask whether language models are sensitive to this discourse function as encoded by Persian ye(k). Linguistic theory for Persian predicts that ye(k)-marked objects support anaphoric uptake more readily than bare objects. Comparing a bare object against a minimally different ye(k)-marked object, we find that both encoder- and decoder-based models assign higher scores to object-anaphoric uptake material after ye(k) contexts. The effect is reliable at the object-anaphoric NP and, in six of seven decoders, exceeds both subject-span and neutral-continuation controls, but is weaker and more model-dependent over the whole continuation. We find a parallel directional effect for an English indefinite-this contrast, showing that a comparable downstream anaphoric-uptake pattern is observable with a different language-specific cue. As a secondary finding, we show that the scoring unit (only the anaphoric uptake site vs. the whole continuation) matters, and that the local site provides a clearer signal. We will release the Persian and English stimulus sets, item-level scores, and reproduction scripts upon publication.</abstract>
<identifier type="citekey">safakar-pado-2026-testing</identifier>
<location>
<url>https://aclanthology.org/2026.mrl-1.14/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>183</start>
<end>195</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Testing Language Model Sensitivity to Object-Anaphoric Accessibility: Persian ye(k) and English indefinite this
%A Safakar, Nikta Yekrang
%A Padó, Sebastian
%Y Adelani, David Ifeoluwa
%Y Alabi, Jesujoba
%Y Arnett, Catherine
%Y Chang, Tyler
%Y Downey, C. M.
%Y Goldman, Omer
%Y Li, Senyu
%Y Miranda, Lester James Validad
%Y Qi, Jirui
%Y Stap, David
%Y Winata, Genta Indra
%Y Zhang, Xinyu Crystina
%S Proceedings of the 6th Workshop on Multilingual Representation Learning (MRL 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-469-9
%F safakar-pado-2026-testing
%X How accessible a discourse referent is for later mention depends on how it is introduced: indefinite marking can make an entity more accessible for anaphora. This dimension is computationally understudied. We ask whether language models are sensitive to this discourse function as encoded by Persian ye(k). Linguistic theory for Persian predicts that ye(k)-marked objects support anaphoric uptake more readily than bare objects. Comparing a bare object against a minimally different ye(k)-marked object, we find that both encoder- and decoder-based models assign higher scores to object-anaphoric uptake material after ye(k) contexts. The effect is reliable at the object-anaphoric NP and, in six of seven decoders, exceeds both subject-span and neutral-continuation controls, but is weaker and more model-dependent over the whole continuation. We find a parallel directional effect for an English indefinite-this contrast, showing that a comparable downstream anaphoric-uptake pattern is observable with a different language-specific cue. As a secondary finding, we show that the scoring unit (only the anaphoric uptake site vs. the whole continuation) matters, and that the local site provides a clearer signal. We will release the Persian and English stimulus sets, item-level scores, and reproduction scripts upon publication.
%U https://aclanthology.org/2026.mrl-1.14/
%P 183-195
Markdown (Informal)
[Testing Language Model Sensitivity to Object-Anaphoric Accessibility: Persian ye(k) and English indefinite this](https://aclanthology.org/2026.mrl-1.14/) (Safakar & Padó, MRL 2026)
ACL