{"slug": "balancing-reasoning-and-hardware-constraints-in-rag-pipelines-for-ukrainian", "title": "Balancing Reasoning and Hardware Constraints in RAG Pipelines for Ukrainian Multi-Domain Document Understanding", "summary": "A resource-efficient Hybrid RAG pipeline using BM25, BGE-M3, and Cross-Encoder reranking scored 0.8095 on the private test set of the UNLP 2026 Shared Task on Multi-Domain Document Understanding, placing 10th out of 15 active teams. The team reported that OCR of scanned Ukrainian PDFs consumed 5-7 hours of the 9-hour offline Kaggle execution limit under sequential single-threaded execution, leaving roughly two hours of LLM inference for 500 questions, so they ran a 4-bit quantized LapaLLM 12B model via llama.cpp on dual NVIDIA T4 GPUs instead of parameter-heavy reasoning models such as DeepSeek R1, which consistently timed out.", "body_md": "arXiv:2609.22124v1 Announce Type: new \nAbstract: 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.", "url": "https://wpnews.pro/news/balancing-reasoning-and-hardware-constraints-in-rag-pipelines-for-ukrainian", "canonical_source": "https://arxiv.org/abs/2609.22124", "published_at": "2026-09-22 04:00:00+00:00", "updated_at": "2026-09-22 04:25:30.216454+00:00", "lang": "en", "topics": ["natural-language-processing", "large-language-models", "ai-research", "ai-infrastructure"], "entities": ["UNLP 2026 Shared Task on Multi-Domain Document Understanding", "Kaggle", "BM25", "BGE-M3", "LapaLLM 12B", "llama.cpp", "NVIDIA T4", "DeepSeek R1"], "alternates": {"html": "https://wpnews.pro/news/balancing-reasoning-and-hardware-constraints-in-rag-pipelines-for-ukrainian", "markdown": "https://wpnews.pro/news/balancing-reasoning-and-hardware-constraints-in-rag-pipelines-for-ukrainian.md", "text": "https://wpnews.pro/news/balancing-reasoning-and-hardware-constraints-in-rag-pipelines-for-ukrainian.txt", "jsonld": "https://wpnews.pro/news/balancing-reasoning-and-hardware-constraints-in-rag-pipelines-for-ukrainian.jsonld"}}