@inproceedings{takenaka-yanaka-2026-seeing,
title = "Seeing the Other Side: Diagnostic Tasks for Viewpoint Reasoning in Vision{--}Language Models",
author = "Takenaka, Makoto and
Yanaka, Hitomi",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.737/",
doi = "10.63317/2b34cz9k64ug",
pages = "9386--9395",
abstract = "Humans can integrate multiple visual perspectives and infer how an object appears from unseen sides. This study investigates whether Large Vision Language Models (LVLMs) exhibit a comparable ability for reference-grounded spatial reasoning. We propose two diagnostic tasks: Opposite-Side Reasoning, which determines whether two images show the same object from opposite viewpoints, and Viewpoint Identification, which predicts the viewpoint of a target image using a reference image and its label. An additional condition, Viewpoint Identification (no-ref), removes reference information to reveal cases solvable without it, distinguishing genuine reasoning from bias-driven shortcuts. Our evaluation shows that both open and proprietary LVLMs fall far short of human performance. Even state-of-the-art proprietary LVLMs with relatively high accuracy retain many correct answers when reference information is removed, suggesting that their success often relies on linguistic or dataset-driven priors rather than genuine reference-based reasoning. These findings indicate that current LVLMs have not yet achieved consistent, reference-grounded spatial reasoning. Our datasets in this work will be released on the Hugging Face Hub to support future research on multimodal viewpoint reasoning and spatial understanding."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="takenaka-yanaka-2026-seeing">
<titleInfo>
<title>Seeing the Other Side: Diagnostic Tasks for Viewpoint Reasoning in Vision–Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Makoto</namePart>
<namePart type="family">Takenaka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitomi</namePart>
<namePart type="family">Yanaka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Humans can integrate multiple visual perspectives and infer how an object appears from unseen sides. This study investigates whether Large Vision Language Models (LVLMs) exhibit a comparable ability for reference-grounded spatial reasoning. We propose two diagnostic tasks: Opposite-Side Reasoning, which determines whether two images show the same object from opposite viewpoints, and Viewpoint Identification, which predicts the viewpoint of a target image using a reference image and its label. An additional condition, Viewpoint Identification (no-ref), removes reference information to reveal cases solvable without it, distinguishing genuine reasoning from bias-driven shortcuts. Our evaluation shows that both open and proprietary LVLMs fall far short of human performance. Even state-of-the-art proprietary LVLMs with relatively high accuracy retain many correct answers when reference information is removed, suggesting that their success often relies on linguistic or dataset-driven priors rather than genuine reference-based reasoning. These findings indicate that current LVLMs have not yet achieved consistent, reference-grounded spatial reasoning. Our datasets in this work will be released on the Hugging Face Hub to support future research on multimodal viewpoint reasoning and spatial understanding.</abstract>
<identifier type="citekey">takenaka-yanaka-2026-seeing</identifier>
<identifier type="doi">10.63317/2b34cz9k64ug</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.737/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>9386</start>
<end>9395</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Seeing the Other Side: Diagnostic Tasks for Viewpoint Reasoning in Vision–Language Models
%A Takenaka, Makoto
%A Yanaka, Hitomi
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F takenaka-yanaka-2026-seeing
%X Humans can integrate multiple visual perspectives and infer how an object appears from unseen sides. This study investigates whether Large Vision Language Models (LVLMs) exhibit a comparable ability for reference-grounded spatial reasoning. We propose two diagnostic tasks: Opposite-Side Reasoning, which determines whether two images show the same object from opposite viewpoints, and Viewpoint Identification, which predicts the viewpoint of a target image using a reference image and its label. An additional condition, Viewpoint Identification (no-ref), removes reference information to reveal cases solvable without it, distinguishing genuine reasoning from bias-driven shortcuts. Our evaluation shows that both open and proprietary LVLMs fall far short of human performance. Even state-of-the-art proprietary LVLMs with relatively high accuracy retain many correct answers when reference information is removed, suggesting that their success often relies on linguistic or dataset-driven priors rather than genuine reference-based reasoning. These findings indicate that current LVLMs have not yet achieved consistent, reference-grounded spatial reasoning. Our datasets in this work will be released on the Hugging Face Hub to support future research on multimodal viewpoint reasoning and spatial understanding.
%R 10.63317/2b34cz9k64ug
%U https://aclanthology.org/2026.lrec-1.737/
%U https://doi.org/10.63317/2b34cz9k64ug
%P 9386-9395
Markdown (Informal)
[Seeing the Other Side: Diagnostic Tasks for Viewpoint Reasoning in Vision–Language Models](https://aclanthology.org/2026.lrec-1.737/) (Takenaka & Yanaka, LREC 2026)
ACL