M-Prometheus: A Suite of Open Multilingual LLM Judges
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912677416140800 |
|---|---|
| author | Pombal, José Yoon, Dongkeun Fernandes, Patrick Wu, Ian Kim, Seungone Rei, Ricardo Neubig, Graham Martins, André F. T. |
| author_facet | Pombal, José Yoon, Dongkeun Fernandes, Patrick Wu, Ian Kim, Seungone Rei, Ricardo Neubig, Graham Martins, André F. T. |
| contents | The use of language models for automatically evaluating long-form text (LLM-as-a-judge) is becoming increasingly common, yet most LLM judges are optimized exclusively for English, with strategies for enhancing their multilingual evaluation capabilities remaining largely unexplored in the current literature. This has created a disparity in the quality of automatic evaluation methods for non-English languages, ultimately hindering the development of models with better multilingual capabilities. To bridge this gap, we introduce M-Prometheus, a suite of open-weight LLM judges ranging from 3B to 14B parameters that can provide both direct assessment and pairwise comparison feedback on multilingual outputs. M-Prometheus models outperform state-of-the-art open LLM judges on multilingual reward benchmarks spanning more than 20 languages, as well as on literary machine translation (MT) evaluation covering 4 language pairs. Furthermore, M-Prometheus models can be leveraged at decoding time to significantly improve generated outputs across all 3 tested languages, showcasing their utility for the development of better multilingual models. Lastly, through extensive ablations, we identify the key factors for obtaining an effective multilingual judge, including backbone model selection and training on synthetic multilingual feedback data instead of translated data. We release our models, training dataset, and code. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_04953 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | M-Prometheus: A Suite of Open Multilingual LLM Judges Pombal, José Yoon, Dongkeun Fernandes, Patrick Wu, Ian Kim, Seungone Rei, Ricardo Neubig, Graham Martins, André F. T. Computation and Language Artificial Intelligence The use of language models for automatically evaluating long-form text (LLM-as-a-judge) is becoming increasingly common, yet most LLM judges are optimized exclusively for English, with strategies for enhancing their multilingual evaluation capabilities remaining largely unexplored in the current literature. This has created a disparity in the quality of automatic evaluation methods for non-English languages, ultimately hindering the development of models with better multilingual capabilities. To bridge this gap, we introduce M-Prometheus, a suite of open-weight LLM judges ranging from 3B to 14B parameters that can provide both direct assessment and pairwise comparison feedback on multilingual outputs. M-Prometheus models outperform state-of-the-art open LLM judges on multilingual reward benchmarks spanning more than 20 languages, as well as on literary machine translation (MT) evaluation covering 4 language pairs. Furthermore, M-Prometheus models can be leveraged at decoding time to significantly improve generated outputs across all 3 tested languages, showcasing their utility for the development of better multilingual models. Lastly, through extensive ablations, we identify the key factors for obtaining an effective multilingual judge, including backbone model selection and training on synthetic multilingual feedback data instead of translated data. We release our models, training dataset, and code. |
| title | M-Prometheus: A Suite of Open Multilingual LLM Judges |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2504.04953 |