Saved in:
Bibliographic Details
Main Authors: Sproat, Richard, Zhao, Tianyu, Jones, Llion
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.12724
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912488212135936
author Sproat, Richard
Zhao, Tianyu
Jones, Llion
author_facet Sproat, Richard
Zhao, Tianyu
Jones, Llion
contents We present TransEvalnia, a prompting-based translation evaluation and ranking system that uses reasoning in performing its evaluations and ranking. This system presents fine-grained evaluations based on a subset of the Multidimensional Quality Metrics (https://themqm.org/), returns an assessment of which translation it deems the best, and provides numerical scores for the various dimensions and for the overall translation. We show that TransEvalnia performs as well as or better than the state-of-the-art MT-Ranker (Moosa et al. 2024) on our own English-Japanese data as well as several language pairs from various WMT shared tasks. Using Anthropic's Claude-3.5-Sonnet and Qwen-2.5-72B-Instruct as the evaluation LLMs, we show that the evaluations returned are deemed highly acceptable to human raters, and that the scores assigned to the translations by Sonnet, as well as other LLMs, correlate well with scores assigned by the human raters. We also note the sensitivity of our system -- as well as MT-Ranker -- to the order in which the translations are presented, and we propose methods to address this position bias. All data, including the system's evaluation and reasoning, human assessments, as well as code is released.
format Preprint
id arxiv_https___arxiv_org_abs_2507_12724
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TransEvalnia: Reasoning-based Evaluation and Ranking of Translations
Sproat, Richard
Zhao, Tianyu
Jones, Llion
Computation and Language
We present TransEvalnia, a prompting-based translation evaluation and ranking system that uses reasoning in performing its evaluations and ranking. This system presents fine-grained evaluations based on a subset of the Multidimensional Quality Metrics (https://themqm.org/), returns an assessment of which translation it deems the best, and provides numerical scores for the various dimensions and for the overall translation. We show that TransEvalnia performs as well as or better than the state-of-the-art MT-Ranker (Moosa et al. 2024) on our own English-Japanese data as well as several language pairs from various WMT shared tasks. Using Anthropic's Claude-3.5-Sonnet and Qwen-2.5-72B-Instruct as the evaluation LLMs, we show that the evaluations returned are deemed highly acceptable to human raters, and that the scores assigned to the translations by Sonnet, as well as other LLMs, correlate well with scores assigned by the human raters. We also note the sensitivity of our system -- as well as MT-Ranker -- to the order in which the translations are presented, and we propose methods to address this position bias. All data, including the system's evaluation and reasoning, human assessments, as well as code is released.
title TransEvalnia: Reasoning-based Evaluation and Ranking of Translations
topic Computation and Language
url https://arxiv.org/abs/2507.12724