# CLewR: Curriculum Learning with Restarts for Machine Translation Preference Learning

arXiv: https://arxiv.org/abs/2601.05858 · HTML: https://mlsanity.com/paper/2601.05858/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in LLM preference optimization methods, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 22 of its 43 references that are in the map.
- First posted on arXiv 9 Jan 2026.

## Placed in

- LLM alignment / RLHF / preference optimisation / [LLM preference optimization methods](https://mlsanity.com/alignment/llm-preference-optimization-methods/)

## Builds on (most cited first, 22 of 22)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation](https://mlsanity.com/paper/2401.08417/) (2024)
- [Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive](https://mlsanity.com/paper/2402.13228/) (2024)
- [Tower: An Open Multilingual Large Language Model for Translation-Related Tasks](https://mlsanity.com/paper/2402.17733/) (2024)
- [Competence-based Curriculum Learning for Neural Machine Translation](https://mlsanity.com/paper/1903.09848/) (2019)
- [Reverse Curriculum Generation for Reinforcement Learning](https://mlsanity.com/paper/1707.05300/) (2017)
- [Curriculum Learning and Minibatch Bucketing in Neural Machine Translation](https://mlsanity.com/paper/1707.09533/) (2017)
- [Norm-Based Curriculum Learning for Neural Machine Translation](https://mlsanity.com/paper/2006.02014/) (2020)
- [Curry-DPO: Enhancing Alignment using Curriculum Learning & Ranked Preferences](https://mlsanity.com/paper/2403.07230/) (2024)
- [Multilingual Machine Translation with Open Large Language Models at Practical Scale: An Empirical Study](https://mlsanity.com/paper/2502.02481/) (2025)
- [Curriculum Direct Preference Optimization for Diffusion and Consistency Models](https://mlsanity.com/paper/2405.13637/) (2024)
- [X-ALMA: Plug & Play Modules and Adaptive Rejection for Quality Translation at Scale](https://mlsanity.com/paper/2410.03115/) (2024)
- [Does the Order of Training Samples Matter? Improving Neural Data-to-Text Generation with Curriculum Learning](https://mlsanity.com/paper/2102.03554/) (2021)
- [Meta-Curriculum Learning for Domain Adaptation in Neural Machine Translation](https://mlsanity.com/paper/2103.02262/) (2021)
- [Dynamic Masking Rate Schedules for MLM Pretraining](https://mlsanity.com/paper/2305.15096/) (2023)
- [A Novel Cartography-Based Curriculum Learning Method Applied on RoNLI: The First Romanian Natural Language Inference Corpus](https://mlsanity.com/paper/2405.11877/) (2024)
- [Density-Based Dynamic Curriculum Learning for Intent Detection](https://mlsanity.com/paper/2108.10674/) (2021)
- [Task-Level Curriculum Learning for Non-Autoregressive Neural Machine Translation](https://mlsanity.com/paper/2007.08772/) (2020)
- [Task-Informed Anti-Curriculum by Masking Improves Downstream Performance on Text](https://mlsanity.com/paper/2502.12953/) (2025)

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

- [XekRung Technical Report](https://mlsanity.com/paper/2605.00072/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have demonstrated competitive performance in zero-shot multilingual machine translation (MT). Some follow-up works further improved MT performance via preference optimization, but they leave a key aspect largely underexplored: the order in which data samples are given during training. We address this topic by integrating curriculum learning into various state-of-the-art preference optimization algorithms to boost MT performance. We introduce a novel curriculum learning strategy with restarts (CLewR), which reiterates easy-to-hard curriculum multiple times during training to effectively mitigate the catastrophic forgetting of easy examples. We demonstrate consistent gains across several model families (Gemma2, Qwen2.5, Llama3.1) and preference optimization techniques. We publicly release our code at https://github.com/alexandra-dragomir/CLewR.