@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://preview.aclanthology.org/ingest-acl-workshops/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"
}