@inproceedings{tang-etal-2026-chengtang,
title = "chengtang at {S}em{E}val-2026 Task 7: A Retrieval-Augmented Generation Framework for Cultural Perspective Alignment in Everyday {MCQ}s",
author = "Tang, Cheng and
Meng, Zhichao and
Jin, Meizhi",
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-1.207/",
pages = "1610--1615",
ISBN = "979-8-89176-414-9",
abstract = "Large language models (LLMs) often exhibit significant cultural representation biases in multilingual everyday knowledge understanding, struggling to accurately capture region-specific customs and values. This paper presents our system submission for SemEval 2026 Task 7: BLEnD Challenge Track 2 (MCQ) (SemEval-2026 Task 7 Organizers, 2026). To address these challenges, we propose a training-free retrieval-augmented generation (RAG) framework. Without introducing any external data, we manuallyconstructed a localized multicultural knowledge base for each language-region and used text-embedding-v4 for region-specific cultural background retrieval. In the generation stage, we adopted a strict zero-shot setting: prompts contain no task instance question-answer examples, only injecting locale-relevant background cultural descriptions via RAG to compensate for contextual information absence, combined with a dual-model ensemble strategy using Gemini 3 Flash (preview) (Google DeepMind, 2025) and GPT-5.2 Chat (OpenAI, 2025). Our system achieved an overall score of 96.35 on the final Evaluation dataset.Additionally, we conducted in-depth analysis of model performance on specific languages, particularly highlighting severe cultural alignment challenges faced by large models in dialectal variants like Moroccan Arabic (ar-MA) and highly localized subjective Japanese (jaJP) everyday scenarios"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tang-etal-2026-chengtang">
<titleInfo>
<title>chengtang at SemEval-2026 Task 7: A Retrieval-Augmented Generation Framework for Cultural Perspective Alignment in Everyday MCQs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Cheng</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhichao</namePart>
<namePart type="family">Meng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meizhi</namePart>
<namePart type="family">Jin</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>Large language models (LLMs) often exhibit significant cultural representation biases in multilingual everyday knowledge understanding, struggling to accurately capture region-specific customs and values. This paper presents our system submission for SemEval 2026 Task 7: BLEnD Challenge Track 2 (MCQ) (SemEval-2026 Task 7 Organizers, 2026). To address these challenges, we propose a training-free retrieval-augmented generation (RAG) framework. Without introducing any external data, we manuallyconstructed a localized multicultural knowledge base for each language-region and used text-embedding-v4 for region-specific cultural background retrieval. In the generation stage, we adopted a strict zero-shot setting: prompts contain no task instance question-answer examples, only injecting locale-relevant background cultural descriptions via RAG to compensate for contextual information absence, combined with a dual-model ensemble strategy using Gemini 3 Flash (preview) (Google DeepMind, 2025) and GPT-5.2 Chat (OpenAI, 2025). Our system achieved an overall score of 96.35 on the final Evaluation dataset.Additionally, we conducted in-depth analysis of model performance on specific languages, particularly highlighting severe cultural alignment challenges faced by large models in dialectal variants like Moroccan Arabic (ar-MA) and highly localized subjective Japanese (jaJP) everyday scenarios</abstract>
<identifier type="citekey">tang-etal-2026-chengtang</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.207/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>1610</start>
<end>1615</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T chengtang at SemEval-2026 Task 7: A Retrieval-Augmented Generation Framework for Cultural Perspective Alignment in Everyday MCQs
%A Tang, Cheng
%A Meng, Zhichao
%A Jin, Meizhi
%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 tang-etal-2026-chengtang
%X Large language models (LLMs) often exhibit significant cultural representation biases in multilingual everyday knowledge understanding, struggling to accurately capture region-specific customs and values. This paper presents our system submission for SemEval 2026 Task 7: BLEnD Challenge Track 2 (MCQ) (SemEval-2026 Task 7 Organizers, 2026). To address these challenges, we propose a training-free retrieval-augmented generation (RAG) framework. Without introducing any external data, we manuallyconstructed a localized multicultural knowledge base for each language-region and used text-embedding-v4 for region-specific cultural background retrieval. In the generation stage, we adopted a strict zero-shot setting: prompts contain no task instance question-answer examples, only injecting locale-relevant background cultural descriptions via RAG to compensate for contextual information absence, combined with a dual-model ensemble strategy using Gemini 3 Flash (preview) (Google DeepMind, 2025) and GPT-5.2 Chat (OpenAI, 2025). Our system achieved an overall score of 96.35 on the final Evaluation dataset.Additionally, we conducted in-depth analysis of model performance on specific languages, particularly highlighting severe cultural alignment challenges faced by large models in dialectal variants like Moroccan Arabic (ar-MA) and highly localized subjective Japanese (jaJP) everyday scenarios
%U https://aclanthology.org/2026.semeval-1.207/
%P 1610-1615
Markdown (Informal)
[chengtang at SemEval-2026 Task 7: A Retrieval-Augmented Generation Framework for Cultural Perspective Alignment in Everyday MCQs](https://aclanthology.org/2026.semeval-1.207/) (Tang et al., SemEval 2026)
ACL