FLANS at SemEval-2026 Task 7: RAG with Open-Sourced Smaller LLMs for Everyday Knowledge Across Diverse Languages and Cultures

TL;DR

This paper presents a system using retrieval augmented generation with open-sourced smaller language models and culturally aware knowledge bases to answer diverse language questions in a privacy-conscious and sustainable manner.

Contribution

We developed culturally aware knowledge bases and integrated open-sourced smaller LLMs with retrieval techniques for multilingual question answering in a shared task.

Findings

Effective use of culturally aware Wikipedia content improved answer relevance.

Open-sourced smaller LLMs with retrieval outperformed baseline models.

Sharing prompts and resources supports reproducibility and further research.

Abstract

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