用开源小模型+文化知识库，提升多语言日常知识问答准确率
FLANS at SemEval-2026 Task 7: RAG with Open-Sourced Smaller LLMs for Everyday Knowledge Across Diverse Languages and Cultures
- 构建文化敏感知识库，融合维基文本与国别摘要
- 在英西中三语上实现90%以上准确率，优于大模型
- 适合关注隐私、可持续性的多语言知识系统开发者
本文介绍我们参与SemEval-2025任务7《跨多元语言与文化的日常知识》的系统方案。针对短答案题（SAQ）和多选题（MCQ）两个子任务，采用基于开源小语言模型（OS-sLLMs）的检索增强生成（RAG）方法。为适配任务需求，我们利用自建关键词列表从维基百科提取文化相关文本与国家特定摘要，构建了文化感知知识库（CulKBs）。此外，系统还集成DuckDuckGo实时在线搜索结果。为保障隐私与可持续性，所有模型部署于Ollama平台，使用开源小模型。我们公开了经优化的提示词及训练曲线数据。测试语言涵盖英语、西班牙语和中文，实验表明该方案在多项指标上表现优异。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。