Fine-tuning translation LLMs on a curated multi-domain document dataset (DocBlocks) with document, chunk, and sentence level instruction formats improves document-level translation quality and speed while preserving sentence-level performance.
On context span needed for machine translation evaluation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Multilingual Contextualization of Large Language Models for Document-Level Machine Translation
Fine-tuning translation LLMs on a curated multi-domain document dataset (DocBlocks) with document, chunk, and sentence level instruction formats improves document-level translation quality and speed while preserving sentence-level performance.