@inproceedings{rykov-etal-2025-looking,
title = "Through the Looking Glass: Common Sense Consistency Evaluation of Weird Images",
author = "Rykov, Elisei and
Petrushina, Kseniia and
Titova, Kseniia and
Razzhigaev, Anton and
Panchenko, Alexander and
Konovalov, Vasily",
editor = "Ebrahimi, Abteen and
Haider, Samar and
Liu, Emmy and
Haider, Sammar and
Leonor Pacheco, Maria and
Wein, Shira",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)",
month = apr,
year = "2025",
address = "Albuquerque, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-srw.28/",
pages = "279--293",
ISBN = "979-8-89176-192-6",
abstract = "Measuring how real images look is a complex task in artificial intelligence research. For example, an image of Albert Einstein holding a smartphone violates common-sense because modern smartphone were invented after Einstein`s death. We introduce a novel method, which we called Through the Looking Glass (TLG), to assess image common sense consistency using Large Vision-Language Models (LVLMs) and Transformer-based encoder. By leveraging LVLM to extract atomic facts from these images, we obtain a mix of accurate facts. We proceed by fine-tuning a compact attention-pooling classifier over encoded atomic facts. Our TLG has achieved a new state-of-the-art performance on the WHOOPS! and WEIRD datasets while leveraging a compact fine-tuning component."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rykov-etal-2025-looking">
<titleInfo>
<title>Through the Looking Glass: Common Sense Consistency Evaluation of Weird Images</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elisei</namePart>
<namePart type="family">Rykov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kseniia</namePart>
<namePart type="family">Petrushina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kseniia</namePart>
<namePart type="family">Titova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anton</namePart>
<namePart type="family">Razzhigaev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Panchenko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vasily</namePart>
<namePart type="family">Konovalov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abteen</namePart>
<namePart type="family">Ebrahimi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samar</namePart>
<namePart type="family">Haider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emmy</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sammar</namePart>
<namePart type="family">Haider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Leonor Pacheco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shira</namePart>
<namePart type="family">Wein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-192-6</identifier>
</relatedItem>
<abstract>Measuring how real images look is a complex task in artificial intelligence research. For example, an image of Albert Einstein holding a smartphone violates common-sense because modern smartphone were invented after Einstein‘s death. We introduce a novel method, which we called Through the Looking Glass (TLG), to assess image common sense consistency using Large Vision-Language Models (LVLMs) and Transformer-based encoder. By leveraging LVLM to extract atomic facts from these images, we obtain a mix of accurate facts. We proceed by fine-tuning a compact attention-pooling classifier over encoded atomic facts. Our TLG has achieved a new state-of-the-art performance on the WHOOPS! and WEIRD datasets while leveraging a compact fine-tuning component.</abstract>
<identifier type="citekey">rykov-etal-2025-looking</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-srw.28/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>279</start>
<end>293</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Through the Looking Glass: Common Sense Consistency Evaluation of Weird Images
%A Rykov, Elisei
%A Petrushina, Kseniia
%A Titova, Kseniia
%A Razzhigaev, Anton
%A Panchenko, Alexander
%A Konovalov, Vasily
%Y Ebrahimi, Abteen
%Y Haider, Samar
%Y Liu, Emmy
%Y Haider, Sammar
%Y Leonor Pacheco, Maria
%Y Wein, Shira
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, USA
%@ 979-8-89176-192-6
%F rykov-etal-2025-looking
%X Measuring how real images look is a complex task in artificial intelligence research. For example, an image of Albert Einstein holding a smartphone violates common-sense because modern smartphone were invented after Einstein‘s death. We introduce a novel method, which we called Through the Looking Glass (TLG), to assess image common sense consistency using Large Vision-Language Models (LVLMs) and Transformer-based encoder. By leveraging LVLM to extract atomic facts from these images, we obtain a mix of accurate facts. We proceed by fine-tuning a compact attention-pooling classifier over encoded atomic facts. Our TLG has achieved a new state-of-the-art performance on the WHOOPS! and WEIRD datasets while leveraging a compact fine-tuning component.
%U https://aclanthology.org/2025.naacl-srw.28/
%P 279-293
Markdown (Informal)
[Through the Looking Glass: Common Sense Consistency Evaluation of Weird Images](https://aclanthology.org/2025.naacl-srw.28/) (Rykov et al., NAACL 2025)
ACL
- Elisei Rykov, Kseniia Petrushina, Kseniia Titova, Anton Razzhigaev, Alexander Panchenko, and Vasily Konovalov. 2025. Through the Looking Glass: Common Sense Consistency Evaluation of Weird Images. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop), pages 279–293, Albuquerque, USA. Association for Computational Linguistics.