An End-to-End Ukrainian RAG for Local Deployment. Optimized Hybrid Search and Lightweight Generation
It provides an efficient, locally deployable QA solution for the Ukrainian language, addressing the need for verifiable AI in low-resource settings.
The paper presents a Retrieval-Augmented Generation system for Ukrainian document QA that achieved 2nd place in the UNLP 2026 Shared Task, demonstrating high-quality local deployment on resource-constrained hardware.
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.