FLANS at SemEval-2026 Task 7: RAG with Open-Sourced Smaller LLMs for Everyday Knowledge Across Diverse Languages and Cultures
This work addresses the challenge of cultural and linguistic diversity in knowledge-based AI systems, but it is incremental as it applies existing RAG methods to a new dataset with custom knowledge bases.
The paper tackled the problem of answering everyday knowledge questions across diverse languages and cultures by using retrieval-augmented generation with open-sourced smaller LLMs, achieving participation in SemEval-2025 Task 7 with tested languages including English, Spanish, and Chinese.
This system paper describes our participation in the SemEval-2025 Task-7 ``Everyday Knowledge Across Diverse Languages and Cultures''. We attended two subtasks, i.e., Track 1: Short Answer Questions (SAQ), and Track 2: Multiple-Choice Questions (MCQ). The methods we used are retrieval augmented generation (RAGs) with open-sourced smaller LLMs (OS-sLLMs). To better adapt to this shared task, we created our own culturally aware knowledge base (CulKBs) by extracting Wikipedia content using keyword lists we prepared. We extracted both culturally-aware wiki-text and country-specific wiki-summary. In addition to the local CulKBs, we also have one system integrating live online search output via DuckDuckGo. Towards better privacy and sustainability, we aimed to deploy smaller LLMs (sLLMs) that are open-sourced on the Ollama platform. We share the prompts we developed using refinement techniques and report the learning curve of such prompts. The tested languages are English, Spanish, and Chinese for both tracks. Our resources and codes are shared via https://github.com/aaronlifenghan/FLANS-2026