Metraipolis › archive › dc_04bcddd5b702
Cloud and On-Premises Deployment of Uzbek Legal RAG via Targeted Retriever Fine-Tuning — arXiv:2608.29284
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.29284
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T08:06:56.305Z
- SHA-256 of the archived text
62757cb2b840581585391b94efa5536ed1491c9aacab174e9b757e4555345ebd- Stable URL of this page
https://metraipolis.com/documento/dc_04bcddd5b702
How to cite
Cloud and On-Premises Deployment of Uzbek Legal RAG via Targeted Retriever Fine-Tuning — arXiv:2608.29284 — arXiv (en), https://arxiv.org/abs/2608.29284 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_04bcddd5b702 (Metraipolis archive dc_04bcddd5b702, sha256 62757cb2b840581585391b94efa5536ed1491c9aacab174e9b757e4555345ebd)
BibTeX
@misc{dc04bcddd5b702,
title = {Cloud and On-Premises Deployment of Uzbek Legal RAG via Targeted Retriever Fine-Tuning — arXiv:2608.29284},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.29284},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_04bcddd5b702; sha256 62757cb2b840581585391b94efa5536ed1491c9aacab174e9b757e4555345ebd},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29284. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Deploying large language models for legal question answering raises challenges that general-purpose leaderboards do not capture, particularly for low-resource languages and under hard operational constraints. We report on building and operating a retrieval-augmented (RAG) legal assistant for Uzbek that must run in two regimes: a managed cloud service that maximizes answer quality within a per-token cost ceiling, and an on-premises deployment for clients whose legal data may not leave their infrastructure, restricting us to open-weight models on limited local hardware under latency constraints. Because no evaluation existed for this setting, we build two domain benchmarks: a retrieval benchmark of 178 expert-annotated legal queries with gold provision spans, and an end-to-end benchmark of 504 expert-curated question--answer pairs scored by an LLM judge whose ratings we validate against human judgments and against an independent-family judge. Applying these benchmarks under each regime, we find the open-versus-proprietary gap is small and cheaply closed by fine-tuning. Therefore, we train UTE-1, which is a state-of-the-art text embedder among open models for Uzbek. We also demonstrate that closing the performance gap via fine-tuning is both impractical due to the intensive hardware demands of long-context legal Q\&A and unnecessary, given that legal acts change frequently. We support this by reporting a negative result from a QLoRA experiment. We distill practical guidance for similar deployments, drawn from a system serving real users in production. We release our benchmarks, evaluation code and the fine-tuned embedder (UTE-1) \href{ this https URL }{at this https URL} to support future work on low-resource legal NLP.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2608.29284 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T07:47:52.687Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).