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

Dimensions overall score 8.0

GitHub Code Pulse

No public code linked for this paper yet.

• The system utilizes retrieval augmented generation (RAG) with open-sourced smaller LLMs (OS-sLLMs) for the SemEval-2025 Task-7.method 70%
• A custom culturally aware knowledge base (CulKBs) was created by extracting Wikipedia content using keyword lists.method 70%
• The system integrates live online search output via DuckDuckGo in addition to local knowledge bases.method 70%
• The system aims to deploy smaller LLMs (sLLMs) that are open-sourced on the Ollama platform for privacy and sustainability.technical 70%
• The system was tested on English, Spanish, and Chinese languages for both SAQ and MCQ tracks.method 70%
• The approach might struggle with extreme edge cases of culturally specific queries not covered by Wikipedia or the curated database.limitation 70%
• The system could disrupt traditional monolingual or culturally singular educational content providers by offering a culturally aware alternative.market 70%
• The system's resources and codes are shared via a GitHub repository.technical 70%

Competitive landscape

Competitor map is still being generated for this paper. Enable generation or check back soon.

Startup potential card