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.
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
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.
It is demonstrated that model selection, retrieval behaviour, and hardware limits must be evaluated separately when deploying open-weight LLMs for Turkish domain documents.
Imtiaz Ul Hassan, Öykü Akbulut, Onur Kaya et al.· arXiv.org· 0 citations
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.· Proceedings of the ACM on Ma...· 0 citations
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
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· news.mit.eduNov 20, 2026
Senior Research Scientist Jim Glass discusses how his MIT-IBM Computing Research Lab collaboration connects perception and language, and addresses the shortcoming of current models.
MIT News · Artificial Intelligence· news.mit.eduNov 19, 2026
An MIT and Dana-Farber Institute-led team used large language models to examine nearly 4,000 studies and hundreds of code repositories, revealing gaps in the information needed to scrutinize and reuse published research.
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.