Skip to content

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

Aug 2026 · 0 citations · 14 references
Computer Science

TL;DR

The system submitted to the UNLP 2026 Shared Task on Multi-Domain Document Understanding achieved a Private Score of 0.8095, placing 10th out of 15 active teams, prioritizing pipeline stability over multi-step reasoning.

Abstract

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.

View source

Similar papers

RAG Pipeline Strategies for Ukrainian Multi-Domain Document Understanding Task

This work developed a modular retrieval-augmented generation (RAG) pipeline and conducted a series of ablation experiments over its individual components to identify the best-performing strategy at each stage, demonstrating that isolated curation of RAG components can yield strong performance for Ukrainian document gro...

М. В. Носенко, Pavlo Kilko, Markus Reuter et al. · 1 citation
#computer vision Preprint Sep 2026

Jina-OCR-v1: Efficient Document Parsing with Speculative Decoding and Dense Verifiable Rewards

Jina-OCR-v1 is presented, an end-to-end document parsing model built to serve on low-budget GPUs that combines the compressed-vision encoder and the 3B mixture-of-experts decoder of DeepSeek-OCR with a FastMTP speculative decoding head that shares a single draft block recursively across K=3 prediction steps.

Alejandro Barón García, Feng Wang, Emília Garcia Casademont et al. · 0 citations
Open access Sep 2026

TACO: Token-Aware Context Optimization for Structured OpenStreetMap Query Generation

Generating executable structured queries for OpenStreetMap (OSM) from natural language remains a challenging task due to the rigid syntax of OverpassQL and the steep learning curve it presents to end-users. While steering Large Language Models (LLMs) via demonstration contexts offers a promising solution, existing...

Zhuoyue Wan, Wentao Hu, Hwanhee Kim et al. · 0 citations
#artificial intelligence Preprint Sep 2026

ESTS at WMT26: Routing-Informed Expert Pruning for Model Compression

Six submissions under the team name ESTS to the unconstrained WMT26 Model Compression Shared Task for English--Simplified Chinese and English--Egyptian Arabic are described, describing how they use task-specific routing mass to rank experts and cross-lingual routing divergence to allocate retained capacity across layer...

Liu O. Martin, Lucas Bandarkar, Nanyun Peng · 0 citations
#machine learning Preprint Sep 2026

Machine-Interpretable Information: Compiling Documents into Searchable and Readable Protocol States

This work introduces Machine-Interpretable Information (MII), the first agent-to-agent (A2A) document-to-state protocol, and demonstrates strong cross-model interoperability across heterogeneous LLMs -- despite the Writer using a legacy GPT-2 vocabulary, forcing genuine semantic translation rather than token-level memo...

Yi-Fan Wang, De-Jing Dou · 0 citations

Related blog posts

MIT News · Artificial Intelligence Nov 17, 2026

Learning the language of machine learning

By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.