@inproceedings{shi-etal-2026-culturally,
title = "Culturally-Aware Image Captioning for {G}uaran{\'i} with Multimodal Prompting: {IUH}oosiers at {A}mericas{NLP} 2026",
author = "Shi, Wenchen and
Artkaew, Phakphum and
Gessler, Luke",
editor = "Mager, Manuel and
Ebrahimi, Abteen and
Bui, Minh Duc and
Pugh, Robert and
Oncevay, Arturo and
Chiruzzo, Luis and
Solano, Rolando Coto and
Rijhwani, Shruti and
Von Der Wense, Katharina",
booktitle = "Proceedings of the Sixth Workshop on {NLP} for Indigenous Languages of the {A}mericas ({A}mericas{NLP})",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.americasnlp-6.21/",
pages = "236--242",
ISBN = "979-8-89176-415-6",
abstract = "The AmericasNLP 2026 shared task challenges systems to generate culturally grounded image captions in indigenous languages of the Americas, a setting that demands both cultural awareness and linguistic accuracy for severely underresourced languages. We present IUHoosiers, Indiana University{'}s system for the Guaran{\'i} track. Rather than fine-tuning, our approach centers on inference-time knowledge injection: for each test image, we retrieve relevant Guaran{\'i} grammatical and cultural resources using BM25 and inject them into a large vision language model{'}s prompt alongside the image, enabling language-specific cultural and linguistic grounding without any parameter updates. IUHoosiers placed first for Guaran{\'i} in both automatic evaluation (24.67 chrF++) and human evaluation (3.45/5), outperforming all other participating systems."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shi-etal-2026-culturally">
<titleInfo>
<title>Culturally-Aware Image Captioning for Guaraní with Multimodal Prompting: IUHoosiers at AmericasNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wenchen</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Phakphum</namePart>
<namePart type="family">Artkaew</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Gessler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth Workshop on NLP for Indigenous Languages of the Americas (AmericasNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Manuel</namePart>
<namePart type="family">Mager</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">Minh</namePart>
<namePart type="given">Duc</namePart>
<namePart type="family">Bui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Pugh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arturo</namePart>
<namePart type="family">Oncevay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rolando</namePart>
<namePart type="given">Coto</namePart>
<namePart type="family">Solano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shruti</namePart>
<namePart type="family">Rijhwani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katharina</namePart>
<namePart type="family">Von Der Wense</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-415-6</identifier>
</relatedItem>
<abstract>The AmericasNLP 2026 shared task challenges systems to generate culturally grounded image captions in indigenous languages of the Americas, a setting that demands both cultural awareness and linguistic accuracy for severely underresourced languages. We present IUHoosiers, Indiana University’s system for the Guaraní track. Rather than fine-tuning, our approach centers on inference-time knowledge injection: for each test image, we retrieve relevant Guaraní grammatical and cultural resources using BM25 and inject them into a large vision language model’s prompt alongside the image, enabling language-specific cultural and linguistic grounding without any parameter updates. IUHoosiers placed first for Guaraní in both automatic evaluation (24.67 chrF++) and human evaluation (3.45/5), outperforming all other participating systems.</abstract>
<identifier type="citekey">shi-etal-2026-culturally</identifier>
<location>
<url>https://aclanthology.org/2026.americasnlp-6.21/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>236</start>
<end>242</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Culturally-Aware Image Captioning for Guaraní with Multimodal Prompting: IUHoosiers at AmericasNLP 2026
%A Shi, Wenchen
%A Artkaew, Phakphum
%A Gessler, Luke
%Y Mager, Manuel
%Y Ebrahimi, Abteen
%Y Bui, Minh Duc
%Y Pugh, Robert
%Y Oncevay, Arturo
%Y Chiruzzo, Luis
%Y Solano, Rolando Coto
%Y Rijhwani, Shruti
%Y Von Der Wense, Katharina
%S Proceedings of the Sixth Workshop on NLP for Indigenous Languages of the Americas (AmericasNLP)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-415-6
%F shi-etal-2026-culturally
%X The AmericasNLP 2026 shared task challenges systems to generate culturally grounded image captions in indigenous languages of the Americas, a setting that demands both cultural awareness and linguistic accuracy for severely underresourced languages. We present IUHoosiers, Indiana University’s system for the Guaraní track. Rather than fine-tuning, our approach centers on inference-time knowledge injection: for each test image, we retrieve relevant Guaraní grammatical and cultural resources using BM25 and inject them into a large vision language model’s prompt alongside the image, enabling language-specific cultural and linguistic grounding without any parameter updates. IUHoosiers placed first for Guaraní in both automatic evaluation (24.67 chrF++) and human evaluation (3.45/5), outperforming all other participating systems.
%U https://aclanthology.org/2026.americasnlp-6.21/
%P 236-242
Markdown (Informal)
[Culturally-Aware Image Captioning for Guaraní with Multimodal Prompting: IUHoosiers at AmericasNLP 2026](https://aclanthology.org/2026.americasnlp-6.21/) (Shi et al., AmericasNLP 2026)
ACL