# A Rising Tide Lifts All Boats: MTQE Rewards for Idioms Improve General Translation Quality

arXiv: https://arxiv.org/abs/2601.06307 · HTML: https://mlsanity.com/paper/2601.06307/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 37 references that are in the map.
- First posted on arXiv 9 Jan 2026.

## Builds on (most cited first, 17 of 17)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [COMET: A Neural Framework for MT Evaluation](https://mlsanity.com/paper/2009.09025/) (2020)
- [Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?](https://mlsanity.com/paper/2504.13837/) (2025)
- [Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models](https://mlsanity.com/paper/2405.01535/) (2024)
- [Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation](https://mlsanity.com/paper/2004.11867/) (2020)
- [Scaling up COMETKIWI: Unbabel-IST 2023 Submission for the Quality Estimation Shared Task](https://mlsanity.com/paper/2309.11925/) (2023)
- [A Study of Reinforcement Learning for Neural Machine Translation](https://mlsanity.com/paper/1808.08866/) (2018)
- [Language Model Alignment in Multilingual Trolley Problems](https://mlsanity.com/paper/2407.02273/) (2024)
- [Improving LLM Abilities in Idiomatic Translation](https://mlsanity.com/paper/2407.03518/) (2024)
- [A Hard Nut to Crack: Idiom Detection with Conversational Large Language Models](https://mlsanity.com/paper/2405.10579/) (2024)
- [Fine-Grained Reward Optimization for Machine Translation using Error Severity Mappings](https://mlsanity.com/paper/2411.05986/) (2024)
- [PETCI: A Parallel English Translation Dataset of Chinese Idioms](https://mlsanity.com/paper/2202.09509/) (2022)
- [From Handcrafted Features to LLMs: A Brief Survey for Machine Translation Quality Estimation](https://mlsanity.com/paper/2403.14118/) (2024)
- [Enhancing Idiomatic Representation in Multiple Languages via an Adaptive Contrastive Triplet Loss](https://mlsanity.com/paper/2406.15175/) (2024)
- [Memorization or Reasoning? Exploring the Idiom Understanding of LLMs](https://mlsanity.com/paper/2505.16216/) (2025)
- [Language Specific Knowledge: Do Models Know Better in X than in English?](https://mlsanity.com/paper/2505.14990/) (2025)

## Built on by (most cited first, 1 of 1)

- [LLMs Get Smarter from Targeted Synthetic Multilingual Data](https://mlsanity.com/paper/2608.15964/) (2026)

## Abstract (arXiv)

Non-compositional expressions (e.g., idioms, proverbs, and metaphors) pose significant challenges for neural machine translation systems because their meanings cannot be derived from individual words alone. These expressions encode rich, cultural meaning, and have both figurative and literal meanings, making accurate translation difficult. Because models are fairly good at translating compositional text, we investigate GRPO-style fine-tuning using Machine Translation Quality Estimation (MTQE) models as reward functions to train models to better translate idioms. Using Chinese and Hindi idiom datasets, we find that idiom translation abilities improve by ~14 points, general, non-idiomatic translation implicitly improves by ~8 points, and cross-lingual translation abilities (trained on one language, evaluated on another) improves by ~6 points. Overall, our work quantifies the non-compositional translation gap and offers insights for developing LLMs with stronger cross-cultural and figurative language understanding.