@inproceedings{siingh-etal-2025-getreason,
title = "{GETR}eason: Enhancing Image Context Extraction through Hierarchical Multi-Agent Reasoning",
author = "Siingh, Shikhhar and
Rawat, Abhinav and
Baral, Chitta and
Gupta, Vivek",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.1439/",
doi = "10.18653/v1/2025.acl-long.1439",
pages = "29779--29800",
ISBN = "979-8-89176-251-0",
abstract = "Publicly significant images from events carry valuable contextual information with applications in domains such as journalism and education. However, existing methodologies often struggle to accurately extract this contextual relevance from images. To address this challenge, we introduce GETREASON (Geospatial Event Temporal Reasoning), a framework designed to go beyond surfacelevel image descriptions and infer deeper contextual meaning. We hypothesize that extracting global event, temporal, and geospatial information from an image enables a more accurate understanding of its contextual significance. We also introduce a new metric GREAT (Geospatial, Reasoning and Event Accuracy with Temporal alignment) for a reasoning capturing evaluation. Our layered multi-agentic approach, evaluated using a reasoning-weighted metric, demonstrates that meaningful information can be inferred from images, allowing them to be effectively linked to their corresponding events and broader contextual background."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="siingh-etal-2025-getreason">
<titleInfo>
<title>GETReason: Enhancing Image Context Extraction through Hierarchical Multi-Agent Reasoning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shikhhar</namePart>
<namePart type="family">Siingh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhinav</namePart>
<namePart type="family">Rawat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chitta</namePart>
<namePart type="family">Baral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Gupta</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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-251-0</identifier>
</relatedItem>
<abstract>Publicly significant images from events carry valuable contextual information with applications in domains such as journalism and education. However, existing methodologies often struggle to accurately extract this contextual relevance from images. To address this challenge, we introduce GETREASON (Geospatial Event Temporal Reasoning), a framework designed to go beyond surfacelevel image descriptions and infer deeper contextual meaning. We hypothesize that extracting global event, temporal, and geospatial information from an image enables a more accurate understanding of its contextual significance. We also introduce a new metric GREAT (Geospatial, Reasoning and Event Accuracy with Temporal alignment) for a reasoning capturing evaluation. Our layered multi-agentic approach, evaluated using a reasoning-weighted metric, demonstrates that meaningful information can be inferred from images, allowing them to be effectively linked to their corresponding events and broader contextual background.</abstract>
<identifier type="citekey">siingh-etal-2025-getreason</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.1439</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.1439/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>29779</start>
<end>29800</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GETReason: Enhancing Image Context Extraction through Hierarchical Multi-Agent Reasoning
%A Siingh, Shikhhar
%A Rawat, Abhinav
%A Baral, Chitta
%A Gupta, Vivek
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F siingh-etal-2025-getreason
%X Publicly significant images from events carry valuable contextual information with applications in domains such as journalism and education. However, existing methodologies often struggle to accurately extract this contextual relevance from images. To address this challenge, we introduce GETREASON (Geospatial Event Temporal Reasoning), a framework designed to go beyond surfacelevel image descriptions and infer deeper contextual meaning. We hypothesize that extracting global event, temporal, and geospatial information from an image enables a more accurate understanding of its contextual significance. We also introduce a new metric GREAT (Geospatial, Reasoning and Event Accuracy with Temporal alignment) for a reasoning capturing evaluation. Our layered multi-agentic approach, evaluated using a reasoning-weighted metric, demonstrates that meaningful information can be inferred from images, allowing them to be effectively linked to their corresponding events and broader contextual background.
%R 10.18653/v1/2025.acl-long.1439
%U https://aclanthology.org/2025.acl-long.1439/
%U https://doi.org/10.18653/v1/2025.acl-long.1439
%P 29779-29800
Markdown (Informal)
[GETReason: Enhancing Image Context Extraction through Hierarchical Multi-Agent Reasoning](https://aclanthology.org/2025.acl-long.1439/) (Siingh et al., ACL 2025)
ACL