# Balancing Reasoning and Hardware Constraints in RAG Pipelines for Ukrainian Multi-Domain Document Understanding

arXiv: https://arxiv.org/abs/2609.22124 · HTML: https://mlsanity.com/paper/2609.22124/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 2 of its 10 references that are in the map.
- First posted on arXiv 20 Aug 2026.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)
- Retrieval-augmented generation / [Multimodal RAG](https://mlsanity.com/rag/multimodal-rag/)

## Builds on (most cited first, 2 of 2)

- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)

## Abstract (arXiv)

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 llama.cpp 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.