An End-to-End Ukrainian RAG for Local Deployment. Optimized Hybrid Search and Lightweight Generation

arXiv:2604.22095v1 Announce Type: new Abstract: 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.

BERAG: Bayesian Ensemble Retrieval-Augmented Generation for Knowledge-based Visual Question Answering
Latent Abstraction for Retrieval-Augmented Generation
Guaranteeing Knowledge Integration with Joint Decoding for Retrieval-Augmented Generation
Improving End-to-End Training of Retrieval-Augmented Generation Models via Joint Stochastic Approximation
Self-Correcting RAG: Enhancing Faithfulness via MMKP Context Selection and NLI-Guided MCTS

Source: arXiv cs.CL | 2026-04-27

Related