@inproceedings{ilinykh-etal-2025-coreference,
title = "Coreference as an indicator of context scope in multimodal narrative",
author = "Ilinykh, Nikolai and
Lappin, Shalom and
Sayeed, Asad B. and
Lo{\'a}iciga, Sharid",
editor = "Arviv, Ofir and
Clinciu, Miruna and
Dhole, Kaustubh and
Dror, Rotem and
Gehrmann, Sebastian and
Habba, Eliya and
Itzhak, Itay and
Mille, Simon and
Perlitz, Yotam and
Santus, Enrico and
Sedoc, Jo{\~a}o and
Shmueli Scheuer, Michal and
Stanovsky, Gabriel and
Tafjord, Oyvind",
booktitle = "Proceedings of the Fourth Workshop on Generation, Evaluation and Metrics (GEM{\texttwosuperior})",
month = jul,
year = "2025",
address = "Vienna, Austria and virtual meeting",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.gem-1.67/",
pages = "789--807",
ISBN = "979-8-89176-261-9",
abstract = "We demonstrate that large multimodal language models differ substantially from humans in the distribution of coreferential expressions in a visual storytelling task. We introduce a number of metrics to quantify the characteristics of coreferential patterns in both human- and machine-written texts. Humans distribute coreferential expressions in a way that maintains consistency across texts and images, interleaving references to different entities in a highly varied way. Machines are less able to track mixed references, despite achieving perceived improvements in generation quality. Materials, metrics, and code for our study are available at https://github.com/GU-CLASP/coreference-context-scope."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ilinykh-etal-2025-coreference">
<titleInfo>
<title>Coreference as an indicator of context scope in multimodal narrative</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikolai</namePart>
<namePart type="family">Ilinykh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shalom</namePart>
<namePart type="family">Lappin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asad</namePart>
<namePart type="given">B</namePart>
<namePart type="family">Sayeed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sharid</namePart>
<namePart type="family">Loáiciga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Workshop on Generation, Evaluation and Metrics (GEM²)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ofir</namePart>
<namePart type="family">Arviv</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miruna</namePart>
<namePart type="family">Clinciu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kaustubh</namePart>
<namePart type="family">Dhole</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rotem</namePart>
<namePart type="family">Dror</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Gehrmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eliya</namePart>
<namePart type="family">Habba</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Itay</namePart>
<namePart type="family">Itzhak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Mille</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yotam</namePart>
<namePart type="family">Perlitz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">João</namePart>
<namePart type="family">Sedoc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michal</namePart>
<namePart type="family">Shmueli Scheuer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriel</namePart>
<namePart type="family">Stanovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oyvind</namePart>
<namePart type="family">Tafjord</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria and virtual meeting</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-261-9</identifier>
</relatedItem>
<abstract>We demonstrate that large multimodal language models differ substantially from humans in the distribution of coreferential expressions in a visual storytelling task. We introduce a number of metrics to quantify the characteristics of coreferential patterns in both human- and machine-written texts. Humans distribute coreferential expressions in a way that maintains consistency across texts and images, interleaving references to different entities in a highly varied way. Machines are less able to track mixed references, despite achieving perceived improvements in generation quality. Materials, metrics, and code for our study are available at https://github.com/GU-CLASP/coreference-context-scope.</abstract>
<identifier type="citekey">ilinykh-etal-2025-coreference</identifier>
<location>
<url>https://aclanthology.org/2025.gem-1.67/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>789</start>
<end>807</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Coreference as an indicator of context scope in multimodal narrative
%A Ilinykh, Nikolai
%A Lappin, Shalom
%A Sayeed, Asad B.
%A Loáiciga, Sharid
%Y Arviv, Ofir
%Y Clinciu, Miruna
%Y Dhole, Kaustubh
%Y Dror, Rotem
%Y Gehrmann, Sebastian
%Y Habba, Eliya
%Y Itzhak, Itay
%Y Mille, Simon
%Y Perlitz, Yotam
%Y Santus, Enrico
%Y Sedoc, João
%Y Shmueli Scheuer, Michal
%Y Stanovsky, Gabriel
%Y Tafjord, Oyvind
%S Proceedings of the Fourth Workshop on Generation, Evaluation and Metrics (GEM²)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria and virtual meeting
%@ 979-8-89176-261-9
%F ilinykh-etal-2025-coreference
%X We demonstrate that large multimodal language models differ substantially from humans in the distribution of coreferential expressions in a visual storytelling task. We introduce a number of metrics to quantify the characteristics of coreferential patterns in both human- and machine-written texts. Humans distribute coreferential expressions in a way that maintains consistency across texts and images, interleaving references to different entities in a highly varied way. Machines are less able to track mixed references, despite achieving perceived improvements in generation quality. Materials, metrics, and code for our study are available at https://github.com/GU-CLASP/coreference-context-scope.
%U https://aclanthology.org/2025.gem-1.67/
%P 789-807
Markdown (Informal)
[Coreference as an indicator of context scope in multimodal narrative](https://aclanthology.org/2025.gem-1.67/) (Ilinykh et al., GEM 2025)
ACL