@inproceedings{jin-etal-2024-winoviz,
title = "{WINOVIZ}: Probing Visual Properties of Objects Under Different States",
author = "Jin, Woojeong and
Srinivasan, Tejas and
Thomason, Jesse and
Ren, Xiang",
editor = "Tafreshi, Shabnam and
Akula, Arjun and
Sedoc, Jo{\~a}o and
Drozd, Aleksandr and
Rogers, Anna and
Rumshisky, Anna",
booktitle = "Proceedings of the Fifth Workshop on Insights from Negative Results in NLP",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.insights-1.14/",
doi = "10.18653/v1/2024.insights-1.14",
pages = "110--123",
abstract = "Humans interpret visual aspects of objects based on contexts. For example, a banana appears brown when rotten and green when unripe. Previous studies focused on language models' grasp of typical object properties. We introduce WINOVIZ, a text-only dataset with 1,380 examples of probing language models' reasoning about diverse visual properties under different contexts. Our task demands pragmatic and visual knowledge reasoning. We also present multi-hop data, a more challenging version requiring multi-step reasoning chains. Experimental findings include: a) GPT-4 excels overall but struggles with multi-hop data. b) Large models perform well in pragmatic reasoning but struggle with visual knowledge reasoning. c) Vision-language models outperform language-only models."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jin-etal-2024-winoviz">
<titleInfo>
<title>WINOVIZ: Probing Visual Properties of Objects Under Different States</title>
</titleInfo>
<name type="personal">
<namePart type="given">Woojeong</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tejas</namePart>
<namePart type="family">Srinivasan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jesse</namePart>
<namePart type="family">Thomason</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Workshop on Insights from Negative Results in NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shabnam</namePart>
<namePart type="family">Tafreshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arjun</namePart>
<namePart type="family">Akula</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">Aleksandr</namePart>
<namePart type="family">Drozd</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Humans interpret visual aspects of objects based on contexts. For example, a banana appears brown when rotten and green when unripe. Previous studies focused on language models’ grasp of typical object properties. We introduce WINOVIZ, a text-only dataset with 1,380 examples of probing language models’ reasoning about diverse visual properties under different contexts. Our task demands pragmatic and visual knowledge reasoning. We also present multi-hop data, a more challenging version requiring multi-step reasoning chains. Experimental findings include: a) GPT-4 excels overall but struggles with multi-hop data. b) Large models perform well in pragmatic reasoning but struggle with visual knowledge reasoning. c) Vision-language models outperform language-only models.</abstract>
<identifier type="citekey">jin-etal-2024-winoviz</identifier>
<identifier type="doi">10.18653/v1/2024.insights-1.14</identifier>
<location>
<url>https://aclanthology.org/2024.insights-1.14/</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>110</start>
<end>123</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T WINOVIZ: Probing Visual Properties of Objects Under Different States
%A Jin, Woojeong
%A Srinivasan, Tejas
%A Thomason, Jesse
%A Ren, Xiang
%Y Tafreshi, Shabnam
%Y Akula, Arjun
%Y Sedoc, João
%Y Drozd, Aleksandr
%Y Rogers, Anna
%Y Rumshisky, Anna
%S Proceedings of the Fifth Workshop on Insights from Negative Results in NLP
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F jin-etal-2024-winoviz
%X Humans interpret visual aspects of objects based on contexts. For example, a banana appears brown when rotten and green when unripe. Previous studies focused on language models’ grasp of typical object properties. We introduce WINOVIZ, a text-only dataset with 1,380 examples of probing language models’ reasoning about diverse visual properties under different contexts. Our task demands pragmatic and visual knowledge reasoning. We also present multi-hop data, a more challenging version requiring multi-step reasoning chains. Experimental findings include: a) GPT-4 excels overall but struggles with multi-hop data. b) Large models perform well in pragmatic reasoning but struggle with visual knowledge reasoning. c) Vision-language models outperform language-only models.
%R 10.18653/v1/2024.insights-1.14
%U https://aclanthology.org/2024.insights-1.14/
%U https://doi.org/10.18653/v1/2024.insights-1.14
%P 110-123
Markdown (Informal)
[WINOVIZ: Probing Visual Properties of Objects Under Different States](https://aclanthology.org/2024.insights-1.14/) (Jin et al., insights 2024)
ACL