mlsanityData to 7 Oct 2026

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

arXiv 2604.22095 ↗First posted 23 Apr 2026cs.CLcited by 0

On the map: Retrieval-augmented generation → RAG robustness and adaptive retrieval

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 11 of its 25 references that are in the map. First posted on arXiv 23 Apr 2026.

Builds on

11 of 25 references.

References · 11

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  4. 2019Passage Re-ranking with BERTcited by 629
  5. 2024Aya Model: An Instruction Finetuned Open-Access Multilingual Language Modelcited by 292
  6. 2023RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Modelscited by 272
  7. 2018Automated Fact Checking: Task formulations, methods and future directionscited by 96
  8. 2021WikiCheck: An end-to-end open source Automatic Fact-Checking API based on Wikipediacited by 12
  9. 2024An Open Multilingual System for Scoring Readability of Wikipediacited by 7
  10. 2023Fair multilingual vandalism detection system for Wikipediacited by 4
  11. 2026From BM25 to Corrective RAG: Benchmarking Retrieval Strategies for Text-and-Table Documentscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Toward Agentic RAG for Ukrainian
  2. 2024PersianRAG: A Retrieval-Augmented Generation System for Persian Language
  3. 2024Retrieval-Augmented Generation for Domain-Specific Question Answering: A Case Study on Pittsburgh and CMU
  4. 2026A Comparative Study of Language Models for Khmer Retrieval-Augmented Question Answering
  5. 2025LLM-Assisted Question-Answering on Technical Documents Using Structured Data-Aware Retrieval Augmented Generation
  6. 2024W-RAG: Weakly Supervised Dense Retrieval in RAG for Open-domain Question Answering
  7. 2024The Power of Noise: Redefining Retrieval for RAG Systems
  8. 2024Leveraging Retrieval-Augmented Generation for Persian University Knowledge Retrieval