VerbaNexAI at SemEval-2026 Task 7: Integrating Web Snippets and RAG for the Evaluation of Multilingual Cultural Knowledge in LLMs
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% global accuracy, while LLaMA-3.2-1B obtained 15.54%. In a large-scale evaluation (30,500 instances), the 1B model achieved 16.69% and maintained stability after prompt optimization. The results demonstrate that contextual retrieval improves the evaluation of multilingual cultural knowledge and highlight the importance of pipeline design and model capacity.