# M-Prometheus: A Suite of Open Multilingual LLM Judges

arXiv: https://arxiv.org/abs/2504.04953 · HTML: https://mlsanity.com/paper/2504.04953/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 37 references that are in the map.
- First posted on arXiv 7 Apr 2025.

## Builds on (most cited first, 18 of 18)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [SoundStream: An End-to-End Neural Audio Codec](https://mlsanity.com/paper/2107.03312/) (2021)
- [Finite Scalar Quantization: VQ-VAE Made Simple](https://mlsanity.com/paper/2309.15505/) (2023)
- [High-Fidelity Audio Compression with Improved RVQGAN](https://mlsanity.com/paper/2306.06546/) (2023)
- [SpeechBrain: A General-Purpose Speech Toolkit](https://mlsanity.com/paper/2106.04624/) (2021)
- [FSD50K: An Open Dataset of Human-Labeled Sound Events](https://mlsanity.com/paper/2010.00475/) (2020)
- [BigVGAN: A Universal Neural Vocoder with Large-Scale Training](https://mlsanity.com/paper/2206.04658/) (2022)
- [Neural Networks Fail to Learn Periodic Functions and How to Fix It](https://mlsanity.com/paper/2006.08195/) (2020)
- [HiFi-Codec: Group-residual Vector quantization for High Fidelity Audio Codec](https://mlsanity.com/paper/2305.02765/) (2023)
- [UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation](https://mlsanity.com/paper/2106.07889/) (2021)
- [Scaling Transformers for Low-Bitrate High-Quality Speech Coding](https://mlsanity.com/paper/2411.19842/) (2024)
- [FunCodec: A Fundamental, Reproducible and Integrable Open-source Toolkit for Neural Speech Codec](https://mlsanity.com/paper/2309.07405/) (2023)
- [DASB - Discrete Audio and Speech Benchmark](https://mlsanity.com/paper/2406.14294/) (2024)
- [Codec-SUPERB: An In-Depth Analysis of Sound Codec Models](https://mlsanity.com/paper/2402.13071/) (2024)
- [Single-Codec: Single-Codebook Speech Codec towards High-Performance Speech Generation](https://mlsanity.com/paper/2406.07422/) (2024)
- [UniCodec: Unified Audio Codec with Single Domain-Adaptive Codebook](https://mlsanity.com/paper/2502.20067/) (2025)
- [Neural Speech Coding for Real-time Communications using Constant Bitrate Scalar Quantization](https://mlsanity.com/paper/2405.08417/) (2024)
- [Analyzing and Mitigating Inconsistency in Discrete Audio Tokens for Neural Codec Language Models](https://mlsanity.com/paper/2409.19283/) (2024)

## Built on by (most cited first, 30 of 38)

- [CodeJudgeBench: Benchmarking LLM-as-a-Judge for Coding Tasks](https://mlsanity.com/paper/2507.10535/) (2025)
- [R3: Robust Rubric-Agnostic Reward Models](https://mlsanity.com/paper/2505.13388/) (2025)
- [One Tokenizer To Rule Them All: Emergent Language Plasticity via Multilingual Tokenizers](https://mlsanity.com/paper/2506.10766/) (2025)
- [LiTransProQA: an LLM-based Literary Translation evaluation metric with Professional Question Answering](https://mlsanity.com/paper/2505.05423/) (2025)
- [IF-RewardBench: Benchmarking Judge Models for Instruction-Following Evaluation](https://mlsanity.com/paper/2603.04738/) (2026)
- [When Life Gives You Samples: The Benefits of Scaling up Inference Compute for Multilingual LLMs](https://mlsanity.com/paper/2506.20544/) (2025)
- [mR3: Multilingual Rubric-Agnostic Reward Reasoning Models](https://mlsanity.com/paper/2510.01146/) (2025)
- [Aligning Agents via Planning: A Benchmark for Trajectory-Level Reward Modeling](https://mlsanity.com/paper/2604.08178/) (2026)
- [Disambiguation in Conversational Question Answering in the Era of LLMs and Agents: A Survey](https://mlsanity.com/paper/2505.12543/) (2025)
- [ToolRM: Towards Agentic Tool-Use Reward Modeling](https://mlsanity.com/paper/2510.26167/) (2025)
- [FairJudge: An Adaptive, Debiased, and Consistent LLM-as-a-Judge](https://mlsanity.com/paper/2602.06625/) (2026)
- [SEADialogues: A Multilingual Culturally Grounded Multi-turn Dialogue Dataset on Southeast Asian Languages](https://mlsanity.com/paper/2508.07069/) (2025)
- [Unveiling Language Routing Isolation in Multilingual MoE Models for Interpretable Subnetwork Adaptation](https://mlsanity.com/paper/2604.03592/) (2026)
- [LLM-as-a-qualitative-judge: automating error analysis in natural language generation](https://mlsanity.com/paper/2506.09147/) (2025)
- [Checklist Engineering Empowers Multilingual LLM Judges](https://mlsanity.com/paper/2507.06774/) (2025)
- [Fairness or Fluency? An Investigation into Language Bias of Pairwise LLM-as-a-Judge](https://mlsanity.com/paper/2601.13649/) (2026)
- [Cross-Lingual LLM-Judge Transfer via Evaluation Decomposition](https://mlsanity.com/paper/2603.18557/) (2026)
- [Mitigating Translationese Bias in Multilingual LLM-as-a-Judge via Disentangled Information Bottleneck](https://mlsanity.com/paper/2603.10351/) (2026)
- [MUG-Eval: A Proxy Evaluation Framework for Multilingual Generation Capabilities in Any Language](https://mlsanity.com/paper/2505.14395/) (2025)
- [Consensus Group Relative Policy Optimization for Text Generation](https://mlsanity.com/paper/2602.03102/) (2026)
- [Bi-Level Prompt Optimization for Multimodal LLM-as-a-Judge](https://mlsanity.com/paper/2602.11340/) (2026)
- [Polyglot Teachers: Evaluating Language Models for Multilingual Synthetic Data Generation](https://mlsanity.com/paper/2604.11290/) (2026)
- [How Hypocritical Is Your LLM judge? Listener-Speaker Asymmetries in the Pragmatic Competence of Large Language Models](https://mlsanity.com/paper/2604.15873/) (2026)
- [Hierarchical Policy Optimization for Simultaneous Translation of Unbounded Speech](https://mlsanity.com/paper/2604.21045/) (2026)
- [Multilinguality at the Edge: Developing Language Models for the Global South](https://mlsanity.com/paper/2604.21637/) (2026)
- [Eye of Judgement: Dissecting the Evaluation of Russian-speaking LLMs with POLLUX](https://mlsanity.com/paper/2505.24616/) (2025)
- [Unlocking Latent Discourse Translation in LLMs Through Quality-Aware Decoding](https://mlsanity.com/paper/2510.06866/) (2025)
- [Comparing Approaches to Automatic Summarization in Less-Resourced Languages](https://mlsanity.com/paper/2512.24410/) (2025)
- [Retell, Reward, Repeat: Reinforcement Learning for Narrative Theory-Informed Story Retelling](https://mlsanity.com/paper/2601.17226/) (2026)
- [BoRP: Bootstrapped Regression Probing for Scalable and Human-Aligned LLM Evaluation](https://mlsanity.com/paper/2601.18253/) (2026)

## Abstract (arXiv)

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.