# Language Imbalance Driven Rewarding for Multilingual Self-improving

arXiv: https://arxiv.org/abs/2410.08964 · HTML: https://mlsanity.com/paper/2410.08964/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Placed in Self-rewarding alignment and self-training, one of 13 directions in Synthetic data and self-improvement for LLMs.
- Builds on 55 of its 70 references that are in the map.
- First posted on arXiv 11 Oct 2024.

## Placed in

- Synthetic data and self-improvement for LLMs / [Self-rewarding alignment and self-training](https://mlsanity.com/synth/self-rewarding-alignment-and-self-training/)

## Builds on (most cited first, 30 of 55)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [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)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [Cross-lingual Language Model Pretraining](https://mlsanity.com/paper/1901.07291/) (2019)
- [AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback](https://mlsanity.com/paper/2305.14387/) (2023)
- [Self-Rewarding Language Models](https://mlsanity.com/paper/2401.10020/) (2024)
- [Language Models are Multilingual Chain-of-Thought Reasoners](https://mlsanity.com/paper/2210.03057/) (2022)
- [InternLM2 Technical Report](https://mlsanity.com/paper/2403.17297/) (2024)
- [Toxicity in ChatGPT: Analyzing Persona-assigned Language Models](https://mlsanity.com/paper/2304.05335/) (2023)
- [Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model](https://mlsanity.com/paper/2402.07827/) (2024)
- [Large Language Models for Mathematical Reasoning: Progresses and Challenges](https://mlsanity.com/paper/2402.00157/) (2024)
- [ZeRO-Infinity: Breaking the GPU Memory Wall for Extreme Scale Deep Learning](https://mlsanity.com/paper/2104.07857/) (2021)
- [Iterative Reasoning Preference Optimization](https://mlsanity.com/paper/2404.19733/) (2024)

## Built on by (most cited first, 28 of 28)

- [Crosslingual Reasoning through Test-Time Scaling](https://mlsanity.com/paper/2505.05408/) (2025)
- [A Survey of Multilingual Reasoning in Language Models](https://mlsanity.com/paper/2502.09457/) (2025)
- [Enhancing LLM Safety Through a Theoretical Minimax Game Lens](https://mlsanity.com/paper/2502.05163/) (2025)
- [MPO: Multilingual Safety Alignment via Reward Gap Optimization](https://mlsanity.com/paper/2505.16869/) (2025)
- [Think Natively: Unlocking Multilingual Reasoning with Consistency-Enhanced Reinforcement Learning](https://mlsanity.com/paper/2510.07300/) (2025)
- [CARE: Multilingual Human Preference Learning for Cultural Awareness](https://mlsanity.com/paper/2504.05154/) (2025)
- [SSR-Zero: Simple Self-Rewarding Reinforcement Learning for Machine Translation](https://mlsanity.com/paper/2505.16637/) (2025)
- [Why Do Multilingual Reasoning Gaps Emerge in Reasoning Language Models?](https://mlsanity.com/paper/2510.27269/) (2025)
- [Aligning LLMs for Multilingual Consistency in Enterprise Applications](https://mlsanity.com/paper/2509.23659/) (2025)
- [Implicit Cross-Lingual Rewarding for Efficient Multilingual Preference Alignment](https://mlsanity.com/paper/2503.04647/) (2025)
- [When Life Gives You Samples: The Benefits of Scaling up Inference Compute for Multilingual LLMs](https://mlsanity.com/paper/2506.20544/) (2025)
- [Align Once, Benefit Multilingually: Enforcing Multilingual Consistency for LLM Safety Alignment](https://mlsanity.com/paper/2602.16660/) (2026)
- [Demystifying Multilingual Chain-of-Thought in Process Reward Modeling](https://mlsanity.com/paper/2502.12663/) (2025)
- [Improving MLLM's Document Image Machine Translation via Synchronously Self-reviewing Its OCR Proficiency](https://mlsanity.com/paper/2507.08309/) (2025)
- [M2PO: Multi-Perspective Multi-Pair Preference Optimization for Machine Translation](https://mlsanity.com/paper/2510.13434/) (2025)
- [CONGRAD:Conflicting Gradient Filtering for Multilingual Preference Alignment](https://mlsanity.com/paper/2503.23777/) (2025)
- [CAPO: Confidence Aware Preference Optimization Learning for Multilingual Preferences](https://mlsanity.com/paper/2511.07691/) (2025)
- [Global-Local Dual Perception for MLLMs in High-Resolution Text-Rich Image Translation](https://mlsanity.com/paper/2602.21956/) (2026)
- [CM-Align: Consistency-based Multilingual Alignment for Large Language Models](https://mlsanity.com/paper/2509.08541/) (2025)
- [Language as a Latent Variable for Reasoning Optimization](https://mlsanity.com/paper/2604.21593/) (2026)
- [Align to the Pivot: Dual Alignment with Self-Feedback for Multilingual Math Reasoning](https://mlsanity.com/paper/2601.17671/) (2026)
- [Learning to Route Languages for Multilingual Policy Optimization](https://mlsanity.com/paper/2605.25360/) (2026)
- [JAI-1: A Thai-Centric Large Language Model](https://mlsanity.com/paper/2510.08620/) (2025)
- [Bilingual Text-to-Motion Generation: A New Benchmark and Baselines](https://mlsanity.com/paper/2603.25178/) (2026)
- [CroCo: Cross-Lingual Contrastive Preference Tuning on Self-Generations](https://mlsanity.com/paper/2605.26293/) (2026)
- [Language Chain in Alignment: Cross-lingual Ranking Preference Optimization](https://mlsanity.com/paper/2608.23149/) (2026)
- [A Systematic Evaluation of Cross-Lingual Consistency Enhancement Methods in Multilingual Language Models](https://mlsanity.com/paper/2609.04409/) (2026)
- [The Limits of BPE Tokenization in Polish: Segmentation-Flexional Forms, Grammatical Anchoring, and First-Person Stability in Inflectional Language Models](https://mlsanity.com/paper/2609.17553/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have achieved state-of-the-art performance across numerous tasks. However, these advancements have predominantly benefited "first-class" languages such as English and Chinese, leaving many other languages underrepresented. This imbalance, while limiting broader applications, generates a natural preference ranking between languages, offering an opportunity to bootstrap the multilingual capabilities of LLM in a self-improving manner. Thus, we propose textitLanguage Imbalance Driven Rewarding, where the inherent imbalance between dominant and non-dominant languages within LLMs is leveraged as a reward signal. Iterative DPO training demonstrates that this approach not only enhances LLM performance in non-dominant languages but also improves the dominant language's capacity, thereby yielding an iterative reward signal. Fine-tuning Meta-Llama-3-8B-Instruct over two iterations of this approach results in continuous improvements in multilingual performance across instruction-following and arithmetic reasoning tasks, evidenced by an average improvement of 7.46% win rate on the X-AlpacaEval leaderboard and 13.9% accuracy on the MGSM benchmark. This work serves as an initial exploration, paving the way for multilingual self-improvement of LLMs. The code is available at https://github.com/ZNLP/Language-Imbalance-Driven-Rewarding