Qwen Goes Brrr: Off-the-Shelf RAG for Ukrainian Multi-Domain Document Understanding

Anton Bazdyrev, Oleksandr Kharytonov, Artur Khodakovskyi, Ivan Havlytskyi, Ivan Bashtovyi


Abstract
We participated in the Fifth UNLP shared task on multi-domain document understanding, where systems must answer Ukrainian multiple-choice questions from PDF collections and localize the supporting document and page. We propose a retrieval-augmented pipeline built around three ideas: contextual chunking of PDFs, question-aware dense retrieval and reranking conditioned on both the question and answer options, and constrained answer generation from a small set of reranked passages. Our final system uses Qwen3-Embedding-8B for retrieval, a fine-tuned Qwen3-Reranker-8B for passage ranking, and Qwen3-32B for answer selection. On a held-out split, reranking improves Recall@1 from 0.6957 to 0.7935, while using the top-2 reranked passages raises answer accuracy from 0.9348 to 0.9674. Our best leaderboard run reached 0.9452 on the public leaderboard and 0.9598 on the private leaderboard. The main lesson of this shared task is that, under strict code-competition constraints, preserving document structure and making relevance estimation aware of the answer space are more important than adding complex downstream heuristics.
Anthology ID:
2026.unlp-1.20
Volume:
Proceedings of the Fifth Ukrainian Natural Language Processing Conference (UNLP 2026)
Month:
May
Year:
2026
Address:
Lviv, Ukraine
Editor:
Mariana Romanyshyn
Venue:
UNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
230–239
Language:
URL:
https://aclanthology.org/2026.unlp-1.20/
DOI:
Bibkey:
Cite (ACL):
Anton Bazdyrev, Oleksandr Kharytonov, Artur Khodakovskyi, Ivan Havlytskyi, and Ivan Bashtovyi. 2026. Qwen Goes Brrr: Off-the-Shelf RAG for Ukrainian Multi-Domain Document Understanding. In Proceedings of the Fifth Ukrainian Natural Language Processing Conference (UNLP 2026), pages 230–239, Lviv, Ukraine. Association for Computational Linguistics.
Cite (Informal):
Qwen Goes Brrr: Off-the-Shelf RAG for Ukrainian Multi-Domain Document Understanding (Bazdyrev et al., UNLP 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.unlp-1.20.pdf