Saved in:
Bibliographic Details
Main Authors: Trokhymovych, Mykola, Oliinyk, Yana, Nyzhnyk, Nazarii
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.22095
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • 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.