@inproceedings{almanza-etal-2026-verbanexai,
title = "{V}erba{N}ex{AI} at {S}em{E}val-2026 Task 7: Integrating Web Snippets and {RAG} for the Evaluation of Multilingual Cultural Knowledge in {LLM}s",
author = "Almanza, Danileth and
Serrano, Jairo and
Puertas, Edwin and
Martinez Santos, Juan Carlos",
editor = "Kochmar, Ekaterina and
Ghosh, Debanjan and
North, Kai and
Komachi, Mamoru",
booktitle = "Proceedings of the 20th {I}nternational {W}orkshop on {S}emantic {E}valuation (2026)",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.semeval-1.123/",
pages = "899--904",
ISBN = "979-8-89176-414-9",
abstract = "In multilingual and multicultural contexts, LLMs require contextualization mechanisms to generate culturally coherent responses. In this sense, this study presents a LLaMA-based approach to answer short cultural questions in different languages within Task 7 of SemEval-2026 (Track 1: SAQ), without access to official training data. The system integrates controlled synthetic data generation, evidence retrieval through web snippets, and a Retrieval-Augmented Generation (RAG) framework with Few-shot learning. BLEnD is used solely as a thematic guide, ensuring semantic independence. During development, the LLaMA-3.1-8B model achieved 38.51{\textbackslash}{\%} global accuracy, while LLaMA-3.2-1B obtained 15.54{\textbackslash}{\%}. In large-scale evaluation (30,500 instances), the 1B model achieved 16.69{\textbackslash}{\%}, maintaining stability after prompt optimization. The results demonstrate that contextual retrieval improves multilingual cultural knowledge evaluation and highlight the importance of pipeline design and model capacity."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="almanza-etal-2026-verbanexai">
<titleInfo>
<title>VerbaNexAI at SemEval-2026 Task 7: Integrating Web Snippets and RAG for the Evaluation of Multilingual Cultural Knowledge in LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Danileth</namePart>
<namePart type="family">Almanza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jairo</namePart>
<namePart type="family">Serrano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Edwin</namePart>
<namePart type="family">Puertas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="given">Carlos</namePart>
<namePart type="family">Martinez Santos</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 20th International Workshop on Semantic Evaluation (2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debanjan</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">North</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mamoru</namePart>
<namePart type="family">Komachi</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">979-8-89176-414-9</identifier>
</relatedItem>
<abstract>In multilingual and multicultural contexts, LLMs require contextualization mechanisms to generate culturally coherent responses. In this sense, this study presents a LLaMA-based approach to answer short cultural questions in different languages within Task 7 of SemEval-2026 (Track 1: SAQ), without access to official training data. The system integrates controlled synthetic data generation, evidence retrieval through web snippets, and a Retrieval-Augmented Generation (RAG) framework with Few-shot learning. BLEnD is used solely as a thematic guide, ensuring semantic independence. During development, the LLaMA-3.1-8B model achieved 38.51\textbackslash% global accuracy, while LLaMA-3.2-1B obtained 15.54\textbackslash%. In large-scale evaluation (30,500 instances), the 1B model achieved 16.69\textbackslash%, maintaining stability after prompt optimization. The results demonstrate that contextual retrieval improves multilingual cultural knowledge evaluation and highlight the importance of pipeline design and model capacity.</abstract>
<identifier type="citekey">almanza-etal-2026-verbanexai</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.123/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>899</start>
<end>904</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T VerbaNexAI at SemEval-2026 Task 7: Integrating Web Snippets and RAG for the Evaluation of Multilingual Cultural Knowledge in LLMs
%A Almanza, Danileth
%A Serrano, Jairo
%A Puertas, Edwin
%A Martinez Santos, Juan Carlos
%Y Kochmar, Ekaterina
%Y Ghosh, Debanjan
%Y North, Kai
%Y Komachi, Mamoru
%S Proceedings of the 20th International Workshop on Semantic Evaluation (2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-414-9
%F almanza-etal-2026-verbanexai
%X In multilingual and multicultural contexts, LLMs require contextualization mechanisms to generate culturally coherent responses. In this sense, this study presents a LLaMA-based approach to answer short cultural questions in different languages within Task 7 of SemEval-2026 (Track 1: SAQ), without access to official training data. The system integrates controlled synthetic data generation, evidence retrieval through web snippets, and a Retrieval-Augmented Generation (RAG) framework with Few-shot learning. BLEnD is used solely as a thematic guide, ensuring semantic independence. During development, the LLaMA-3.1-8B model achieved 38.51\textbackslash% global accuracy, while LLaMA-3.2-1B obtained 15.54\textbackslash%. In large-scale evaluation (30,500 instances), the 1B model achieved 16.69\textbackslash%, maintaining stability after prompt optimization. The results demonstrate that contextual retrieval improves multilingual cultural knowledge evaluation and highlight the importance of pipeline design and model capacity.
%U https://aclanthology.org/2026.semeval-1.123/
%P 899-904
Markdown (Informal)
[VerbaNexAI at SemEval-2026 Task 7: Integrating Web Snippets and RAG for the Evaluation of Multilingual Cultural Knowledge in LLMs](https://aclanthology.org/2026.semeval-1.123/) (Almanza et al., SemEval 2026)
ACL