Metraipolis › archive › dc_c0330d3735ca

Balancing Reasoning and Hardware Constraints in RAG Pipelines for Ukrainian Multi-Domain Document Understanding — arXiv:2609.22124

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.22124
License (as archived)
CC0-1.0
Archived
2026-10-09T06:48:52.208Z
SHA-256 of the archived text
c6b44c76098c2e1edabdf47ec06813894d1bbcc95d3268808c12abd435687926
Stable URL of this page
https://metraipolis.com/documento/dc_c0330d3735ca

How to cite

Balancing Reasoning and Hardware Constraints in RAG Pipelines for Ukrainian Multi-Domain Document Understanding — arXiv:2609.22124 — arXiv (en), https://arxiv.org/abs/2609.22124 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c0330d3735ca (Metraipolis archive dc_c0330d3735ca, sha256 c6b44c76098c2e1edabdf47ec06813894d1bbcc95d3268808c12abd435687926)
BibTeX
@misc{dcc0330d3735ca,
  title = {Balancing Reasoning and Hardware Constraints in RAG Pipelines for Ukrainian Multi-Domain Document Understanding — arXiv:2609.22124},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.22124},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c0330d3735ca; sha256 c6b44c76098c2e1edabdf47ec06813894d1bbcc95d3268808c12abd435687926},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.22124. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This paper describes the system submitted to the UNLP 2026 Shared Task on Multi-Domain Document Understanding. The challenge required extracting precise answers, document IDs, and page numbers from a diverse corpus of Ukrainian PDF documents within a strict 9-hour offline Kaggle execution limit. During evaluation on the hidden private test set, optical character recognition (OCR) of scanned documents emerged as a severe bottleneck, consuming 5-7 hours of the total time budget due to sequential single-threaded execution. This overhead strictly limited the remaining time for Large Language Model (LLM) inference to approximately two hours for 500 questions. To guarantee pipeline completion without timeouts, we developed a resource-efficient Hybrid Retrieval-Augmented Generation (RAG) pipeline utilizing BM25, BGE-M3, and Cross-Encoder reranking. Rather than deploying parameter-heavy reasoning models (e.g., DeepSeek R1) which consistently timed out, we utilized a 4-bit quantized LapaLLM 12B model via this http URL on dual NVIDIA T4 GPUs. Prioritizing pipeline stability over multi-step reasoning, our system achieved a Private Score of 0.8095, placing 10th out of 15 active teams.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Digital Libraries (cs.DL).
Pagina del lavoro: https://arxiv.org/abs/2609.22124 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-09T06:48:44.833Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).