Contextual Refinement of Translations: Large Language Models for Sentence and Document-Level Post-Editing

Large language models (LLMs) have demonstrated considerable success in various natu-
ral language processing tasks, but open-source
LLMs have yet to attain state-of-the-art performance in Neural Machine Translation (NMT).
Nevertheless, their significant performance in tasks demanding a broad understanding and
contextual processing shows their potential for translation. To exploit these abilities, we in-
vestigate using LLMs for MT and explore recent parameter-efficient fine-tuning techniques.
Surprisingly, our initial experiments found that fine-tuning with Q-LoRA for translation pur-
poses led to performance improvements in terms of BLEU but degradation in COMET
compared to in-context learning. To overcome this, we propose an alternative approach: adapt-
ing LLMs as Automatic Post-Editors (APE) rather than direct translators. Building on the
ability of the LLM to handle long sequences, we also propose extending our approach to
document-level translation. We show that leveraging Low-Rank-Adapter fine-tuning for APE
can yield significant improvements across both sentence and document-level metrics while gen-
eralizing to out-of-domain data. ... mehrMost notably, we achieve a state-of-the-art accuracy rate of
88.7% on the ContraPro test set, which assesses the model’s ability to resolve pronoun
ambiguities when translating from English to German. Lastly, during manual post-editing
for document-level translation, the source sentences are iteratively annotated, which can be
used to refine further translations in the document. Here, we demonstrate that leveraging
human corrections can significantly reduce the number of edits required for subsequent trans-
lations.