Saved in:
Bibliographic Details
Main Authors: Mrozinski, Krzysztof, Kang, Minji, Khota, Ahmed, Sutanto, Vincent Michael, De Giacomo, Giovanni Gatti
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.08870
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917001473032192
author Mrozinski, Krzysztof
Kang, Minji
Khota, Ahmed
Sutanto, Vincent Michael
De Giacomo, Giovanni Gatti
author_facet Mrozinski, Krzysztof
Kang, Minji
Khota, Ahmed
Sutanto, Vincent Michael
De Giacomo, Giovanni Gatti
contents Quality estimation (QE) reranking is a form of quality-aware decoding which aims to improve machine translation (MT) by scoring and selecting the best candidate from a pool of generated translations. While known to be effective at the sentence level, its application to the increasingly prominent domain of document-level translation remains underexplored. In this work, we evaluate QE reranking performance on document-level (rather than the typical sentence-level) translation, using various learned and large language model (LLM)-based QE metrics. We find that with our best learned metric, SLIDE, BLEURT-20 scores improve by +2.00 with only two candidates, and by +5.09 with 32, across both decoder-only LLM models and encoder-decoder neural machine translation (NMT) models. Using the best LLM-based metric, GEMBA-DA, gains of +1.63 and +4.30 are achieved under the same conditions. Although gains shrink with longer inputs, reranking with 32 candidates yields improvements of +2.34 (SLIDE) and +1.40 (GEMBA-DA) on our longest documents (512-1024 source tokens). These findings demonstrate the practical value of document-level QE, with minimal runtime overhead given suitable translation models and hardware.
format Preprint
id arxiv_https___arxiv_org_abs_2510_08870
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Quality Estimation Reranking for Document-Level Translation
Mrozinski, Krzysztof
Kang, Minji
Khota, Ahmed
Sutanto, Vincent Michael
De Giacomo, Giovanni Gatti
Computation and Language
Quality estimation (QE) reranking is a form of quality-aware decoding which aims to improve machine translation (MT) by scoring and selecting the best candidate from a pool of generated translations. While known to be effective at the sentence level, its application to the increasingly prominent domain of document-level translation remains underexplored. In this work, we evaluate QE reranking performance on document-level (rather than the typical sentence-level) translation, using various learned and large language model (LLM)-based QE metrics. We find that with our best learned metric, SLIDE, BLEURT-20 scores improve by +2.00 with only two candidates, and by +5.09 with 32, across both decoder-only LLM models and encoder-decoder neural machine translation (NMT) models. Using the best LLM-based metric, GEMBA-DA, gains of +1.63 and +4.30 are achieved under the same conditions. Although gains shrink with longer inputs, reranking with 32 candidates yields improvements of +2.34 (SLIDE) and +1.40 (GEMBA-DA) on our longest documents (512-1024 source tokens). These findings demonstrate the practical value of document-level QE, with minimal runtime overhead given suitable translation models and hardware.
title Quality Estimation Reranking for Document-Level Translation
topic Computation and Language
url https://arxiv.org/abs/2510.08870