本地部署的乌克兰语问答系统，高效准确且低资源消耗。
An End-to-End Ukrainian RAG for Local Deployment. Optimized Hybrid Search and Lightweight Generation
- 两阶段检索+合成数据微调的乌克兰语模型
- 在有限算力下实现高准确率且可验证的回答
- 专为资源受限设备优化的轻量化部署方案
本文提出一种针对乌克兰语文档问答的端到端检索增强生成系统，在UNLP 2026共享任务中获得第二名。系统采用定制的两阶段检索流程获取相关文档页，并结合在合成数据上微调的乌克兰语语言模型生成准确、有依据的答案。最后通过模型压缩实现轻量级本地部署。在严格计算资源限制下，该架构证明了在不牺牲准确性的前提下，可在资源受限硬件上实现高质量、可验证的AI问答。
原文摘要 · Abstract (English)
This paper presents a highly efficient Retrieval-Augmented Generation (RAG) system built specifically for Ukrainian document question answering, which achieved 2nd place in the UNLP 2026 Shared Task. Our solution features a custom two-stage search pipeline that retrieves relevant document pages, paired with a specialized Ukrainian language model fine-tuned on synthetic data to generate accurate, grounded answers. Finally, we compress the model for lightweight deployment. Evaluated under strict computational limits, our architecture demonstrates that high-quality, verifiable AI question answering can be achieved locally on resource-constrained hardware without sacrificing accuracy.
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。