# Implicit Cross-Lingual Rewarding for Efficient Multilingual Preference Alignment

arXiv: https://arxiv.org/abs/2503.04647 · HTML: https://mlsanity.com/paper/2503.04647/

## Key facts

- Cited by 9 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 34 of its 49 references that are in the map.
- First posted on arXiv 6 Mar 2025.

## Placed in

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

## Builds on (most cited first, 30 of 34)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [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)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [LIMA: Less Is More for Alignment](https://mlsanity.com/paper/2305.11206/) (2023)
- [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://mlsanity.com/paper/2405.14734/) (2024)
- [A General Theoretical Paradigm to Understand Learning from Human Preferences](https://mlsanity.com/paper/2310.12036/) (2023)
- [Enhancing Chat Language Models by Scaling High-quality Instructional Conversations](https://mlsanity.com/paper/2305.14233/) (2023)
- [Self-Rewarding Language Models](https://mlsanity.com/paper/2401.10020/) (2024)
- [ZeRO-Infinity: Breaking the GPU Memory Wall for Extreme Scale Deep Learning](https://mlsanity.com/paper/2104.07857/) (2021)
- [From r to Q^*: Your Language Model is Secretly a Q-Function](https://mlsanity.com/paper/2404.12358/) (2024)
- [Okapi: Instruction-tuned Large Language Models in Multiple Languages with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2307.16039/) (2023)
- [DPO Meets PPO: Reinforced Token Optimization for RLHF](https://mlsanity.com/paper/2404.18922/) (2024)
- [Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback](https://mlsanity.com/paper/2406.09279/) (2024)
- [The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm](https://mlsanity.com/paper/2406.18682/) (2024)
- [MAPO: Advancing Multilingual Reasoning through Multilingual Alignment-as-Preference Optimization](https://mlsanity.com/paper/2401.06838/) (2024)
- [BigTranslate: Augmenting Large Language Models with Multilingual Translation Capability over 100 Languages](https://mlsanity.com/paper/2305.18098/) (2023)
- [Bootstrapping Language Models with DPO Implicit Rewards](https://mlsanity.com/paper/2406.09760/) (2024)
- [RLHF Can Speak Many Languages: Unlocking Multilingual Preference Optimization for LLMs](https://mlsanity.com/paper/2407.02552/) (2024)
- [PLUG: Leveraging Pivot Language in Cross-Lingual Instruction Tuning](https://mlsanity.com/paper/2311.08711/) (2023)
- [Improving In-context Learning of Multilingual Generative Language Models with Cross-lingual Alignment](https://mlsanity.com/paper/2311.08089/) (2023)
- [Language Imbalance Driven Rewarding for Multilingual Self-improving](https://mlsanity.com/paper/2410.08964/) (2024)
- [Reuse Your Rewards: Reward Model Transfer for Zero-Shot Cross-Lingual Alignment](https://mlsanity.com/paper/2404.12318/) (2024)

## Built on by (most cited first, 9 of 9)

- [ACE-RL: Adaptive Constraint-Enhanced Reward for Long-form Generation Reinforcement Learning](https://mlsanity.com/paper/2509.04903/) (2025)
- [Improving MLLM's Document Image Machine Translation via Synchronously Self-reviewing Its OCR Proficiency](https://mlsanity.com/paper/2507.08309/) (2025)
- [Parallel Scaling Law: Unveiling Reasoning Generalization through A Cross-Linguistic Perspective](https://mlsanity.com/paper/2510.02272/) (2025)
- [CONGRAD:Conflicting Gradient Filtering for Multilingual Preference Alignment](https://mlsanity.com/paper/2503.23777/) (2025)
- [Structuring the Space of Sociotechnical Alignment](https://mlsanity.com/paper/2607.01250/) (2026)
- [ICDAR 2025 Competition on End-to-End Document Image Machine Translation Towards Complex Layouts](https://mlsanity.com/paper/2603.09392/) (2026)
- [HiMed: Incentivizing Hindi Reasoning in Medical LLMs](https://mlsanity.com/paper/2605.24635/) (2026)
- [Language Chain in Alignment: Cross-lingual Ranking Preference Optimization](https://mlsanity.com/paper/2608.23149/) (2026)
- [PlurVA-LLM-2026 Shared Task Track-1: Pluralistic Value Alignment in LLMs via Multilingual Fine-Tuning and Threshold Calibration](https://mlsanity.com/paper/2609.32382/) (2026)

## Abstract (arXiv)

Direct Preference Optimization (DPO) has become a prominent method for aligning Large Language Models (LLMs) with human preferences. While DPO has enabled significant progress in aligning English LLMs, multilingual preference alignment is hampered by data scarcity. To address this, we propose a novel approach that textitcaptures learned preferences from well-aligned English models by implicit rewards and textittransfers them to other languages through iterative training. Specifically, we derive an implicit reward model from the logits of an English DPO-aligned model and its corresponding reference model. This reward model is then leveraged to annotate preference relations in cross-lingual instruction-following pairs, using English instructions to evaluate multilingual responses. The annotated data is subsequently used for multilingual DPO fine-tuning, facilitating preference knowledge transfer from English to other languages. Fine-tuning Llama3 for two iterations resulted in a 12.72% average improvement in Win Rate and a 5.97% increase in Length Control Win Rate across all training languages on the X-AlpacaEval leaderboard. Our findings demonstrate that leveraging existing English-aligned models can enable efficient and effective multilingual preference alignment, significantly reducing the need for extensive multilingual preference data. The code is available at https://github.com/ZNLP/Implicit-Cross-Lingual-Rewarding