mlsanityData to 7 Oct 2026

GRRM: Group Relative Reward Modeling for Machine Translation

arXiv 2602.14028 ↗First posted 15 Feb 2026cs.CLcited by 2

On the map: LLM reasoning → Reinforcement learning for reasoning

also in 1 more
Abstract (arXiv)

While Group Relative Policy Optimization (GRPO) offers a powerful framework for LLM post-training, its effectiveness in open-ended domains like Machine Translation hinges on accurate intra-group ranking. We identify that standard Pointwise Quality Metrics (PQM) fall short in this context: candidates are evaluated in isolation, so the comparative context is missing for distinguishing fine-grained linguistic nuances. To address this, we introduce the Group Quality Metric (GQM) paradigm and its instantiation, the Group Relative Reward Model (GRRM). Unlike traditional independent scorers, GRRM jointly processes the entire candidate group, leveraging comparative analysis to rigorously resolve relative quality and adaptive granularity. Empirical evaluations confirm that GRRM achieves competitive ranking accuracy among all baselines; integrating GRRM into the GRPO training not only improves general translation quality but also unlocks reasoning capabilities comparable to state-of-the-art reasoning models. We release codes, datasets, and model checkpoints at https://github.com/NJUNLP/GRRM.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning. Builds on 24 of its 35 references that are in the map. First posted on arXiv 15 Feb 2026.

Builds on

24 of 35 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025Understanding R1-Zero-Like Training: A Critical Perspective26 Mar
  2. 2024Generative Verifiers: Reward Modeling as Next-Token Prediction27 Aug

Other references · 22

  1. 2020BLEURT: Learning Robust Metrics for Text Generationcited by 1,196
  2. 2020COMET: A Neural Framework for MT Evaluationcited by 1,024
  3. 2023Large Language Models Are State-of-the-Art Evaluators of Translation Qualitycited by 416
  4. 2023JudgeLM: Fine-tuned Large Language Models are Scalable Judgescited by 351
  5. 2021Experts, Errors, and Context: A Large-Scale Study of Human Evaluation for Machine Translationcited by 333
  6. 2022CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Taskcited by 205
  7. 2024Tower: An Open Multilingual Large Language Model for Translation-Related Taskscited by 205
  8. 2023GEMBA-MQM: Detecting Translation Quality Error Spans with GPT-4cited by 143
  9. 2023Scaling up COMETKIWI: Unbabel-IST 2023 Submission for the Quality Estimation Shared Taskcited by 88
  10. 2025WMT24++: Expanding the Language Coverage of WMT24 to 55 Languages & Dialectscited by 79
  11. 2025MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learningcited by 48
  12. 2024TEaR: Improving LLM-based Machine Translation with Systematic Self-Refinementcited by 37
10 more
  1. 2024DRT: Deep Reasoning Translation via Long Chain-of-Thoughtcited by 28
  2. 2025Evaluating o1-Like LLMs: Unlocking Reasoning for Translation through Comprehensive Analysiscited by 26
  3. 2025PairJudge RM: Perform Best-of-N Sampling with Knockout Tournamentcited by 21
  4. 2025Seed-X: Building Strong Multilingual Translation LLM with 7B Parameterscited by 21
  5. 2025New Trends for Modern Machine Translation with Large Reasoning Modelscited by 17
  6. 2024MT-Ranker: Reference-free machine translation evaluation by inter-system rankingcited by 14
  7. 2025SSR-Zero: Simple Self-Rewarding Reinforcement Learning for Machine Translationcited by 13
  8. 2025ExTrans: Multilingual Deep Reasoning Translation via Exemplar-Enhanced Reinforcement Learningcited by 11
  9. 2025LLM Reasoning for Machine Translation: Synthetic Data Generation over Thinking Tokenscited by 4
  10. 2025EnAnchored-X2X: English-Anchored Optimization for Many-to-Many Translationcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Groupwise Agentic Grading and Advantage Redistribution for Code Agent RLcited by 1
  2. 2026Reference-Free Reinforcement Learning Fine-Tuning for MT: A Seq2Seq Perspectivecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Group Causal Policy Optimization for Post-Training Large Language Models
  2. 2025GVPO: Group Variance Policy Optimization for Large Language Model Post-Training
  3. 2026CoDistill-GRPO: A Co-Distillation Recipe for Efficient Group Relative Policy Optimization
  4. 2026GVPO++: Group Variance Policy Optimization for LLM Post-Training and On-Policy Distillation
  5. 2026Demystifying Group Relative Policy Optimization: Its Policy Gradient is a U-Statistic
  6. 2026Consensus Group Relative Policy Optimization for Text Generation
  7. 2025Token-Level Policy Optimization: Linking Group-Level Rewards to Token-Level Aggregation via Markov Likelihood
  8. 2025GTPO: Stabilizing Group Relative Policy Optimization via Gradient and Entropy Control