Implicit Cross-Lingual Rewarding for Efficient Multilingual Preference Alignment

• URL: http://arxiv.org/abs/2503.04647v2
• Date: Thu, 05 Jun 2025 02:40:44 GMT
• Title: Implicit Cross-Lingual Rewarding for Efficient Multilingual Preference Alignment
• Authors: Wen Yang, Junhong Wu, Chen Wang, Chengqing Zong, Jiajun Zhang,
• Abstract summary: We propose a novel approach that captures preferences from well-aligned English models by implicit rewards and transfers them to other languages through iterative training.<n>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.
• Score: 35.1576728251478
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 $\textit{captures}$ learned preferences from well-aligned English models by implicit rewards and $\textit{transfers}$ 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

Related papers

• Optimizing Language Models for Crosslingual Knowledge Consistency [90.86445137816942]
  Large language models are known to often exhibit inconsistent knowledge.<n>This is particularly problematic in multilingual scenarios, where models are likely to be asked similar questions in different languages.<n>In this work, we show that this issue can be mitigated using reinforcement learning with a structured reward function.
  arXiv  Detail & Related papers  (2026-03-04T23:36:55Z)
• CM-Align: Consistency-based Multilingual Alignment for Large Language Models [84.19366314925593]
  We propose a consistency-based data method to construct high-quality multilingual preference data.<n> Specifically, our method includes two parts: consistency-guided English reference selection and cross-lingual consistency-based multilingual preference data construction.
  arXiv  Detail & Related papers  (2025-09-10T12:40:49Z)
• Seed-X: Building Strong Multilingual Translation LLM with 7B Parameters [53.59868121093848]
  We introduce Seed-X, a family of open-source language models (LLMs) with 7B parameter size.<n>The base model is pre-trained on a diverse, high-quality dataset encompassing both monolingual and bilingual content across 28 languages.<n>The instruct model is then finetuned to translate by Chain-of-Thought (CoT) reasoning and further enhanced through reinforcement learning (RL) to achieve better generalization across diverse language pairs.
  arXiv  Detail & Related papers  (2025-07-18T03:19:43Z)
• MuRating: A High Quality Data Selecting Approach to Multilingual Large Language Model Pretraining [27.952041404675846]
  We introduce MuRating, a framework that transfers high-quality English data-quality signals into a single rater for 17 target languages.<n>MuRating aggregates multiple English "raters" via pairwise comparisons to learn unified document-quality scores.<n>It then projects these judgments through translation to train a multilingual evaluator on monolingual, cross-lingual, and parallel text pairs.
  arXiv  Detail & Related papers  (2025-07-02T15:11:12Z)
• Breaking the Script Barrier in Multilingual Pre-Trained Language Models with Transliteration-Based Post-Training Alignment [50.27950279695363]
  The transfer performance is often hindered when a low-resource target language is written in a different script than the high-resource source language. Inspired by recent work that uses transliteration to address this problem, our paper proposes a transliteration-based post-pretraining alignment (PPA) method.
  arXiv  Detail & Related papers  (2024-06-28T08:59:24Z)
• Crosslingual Capabilities and Knowledge Barriers in Multilingual Large Language Models [62.91524967852552]
  Large language models (LLMs) are typically multilingual due to pretraining on diverse multilingual corpora. But can these models relate corresponding concepts across languages, i.e., be crosslingual? This study evaluates state-of-the-art LLMs on inherently crosslingual tasks.
  arXiv  Detail & Related papers  (2024-06-23T15:15:17Z)
• Reuse Your Rewards: Reward Model Transfer for Zero-Shot Cross-Lingual Alignment [39.94156255629528]
  We evaluate a simple approach for zero-shot cross-lingual alignment. Cross-lingually aligned models are preferred by humans over unaligned models. A different-language reward model sometimes yields better aligned models than a same-language reward model.
  arXiv  Detail & Related papers  (2024-04-18T16:52:36Z)
• Self-Augmentation Improves Zero-Shot Cross-Lingual Transfer [92.80671770992572]
  Cross-lingual transfer is a central task in multilingual NLP. Earlier efforts on this task use parallel corpora, bilingual dictionaries, or other annotated alignment data. We propose a simple yet effective method, SALT, to improve the zero-shot cross-lingual transfer.
  arXiv  Detail & Related papers  (2023-09-19T19:30:56Z)
• Efficiently Aligned Cross-Lingual Transfer Learning for Conversational Tasks using Prompt-Tuning [98.60739735409243]
  Cross-lingual transfer of language models trained on high-resource languages like English has been widely studied for many NLP tasks. We introduce XSGD for cross-lingual alignment pretraining, a parallel and large-scale multilingual conversation dataset. To facilitate aligned cross-lingual representations, we develop an efficient prompt-tuning-based method for learning alignment prompts.
  arXiv  Detail & Related papers  (2023-04-03T18:46:01Z)
• Language-Family Adapters for Low-Resource Multilingual Neural Machine Translation [129.99918589405675]
  Large multilingual models trained with self-supervision achieve state-of-the-art results in a wide range of natural language processing tasks. Multilingual fine-tuning improves performance on low-resource languages but requires modifying the entire model and can be prohibitively expensive. We propose training language-family adapters on top of mBART-50 to facilitate cross-lingual transfer.
  arXiv  Detail & Related papers  (2022-09-30T05:02:42Z)
• Bilingual Alignment Pre-training for Zero-shot Cross-lingual Transfer [33.680292990007366]
  In this paper, we aim to improve the zero-shot cross-lingual transfer performance by aligning the embeddings better. We propose a pre-training task named Alignment Language Model (AlignLM) which uses the statistical alignment information as the prior knowledge to guide bilingual word prediction. The results show AlignLM can improve the zero-shot performance significantly on MLQA and XNLI datasets.
  arXiv  Detail & Related papers  (2021-06-03T10:18:43Z)
• Multilingual Transfer Learning for QA Using Translation as Data Augmentation [13.434957024596898]
  We explore strategies that improve cross-lingual transfer by bringing the multilingual embeddings closer in the semantic space. We propose two novel strategies, language adversarial training and language arbitration framework, which significantly improve the (zero-resource) cross-lingual transfer performance. Empirically, we show that the proposed models outperform the previous zero-shot baseline on the recently introduced multilingual MLQA and TyDiQA datasets.
  arXiv  Detail & Related papers  (2020-12-10T20:29:34Z)
• Mixed-Lingual Pre-training for Cross-lingual Summarization [54.4823498438831]
  Cross-lingual Summarization aims at producing a summary in the target language for an article in the source language. We propose a solution based on mixed-lingual pre-training that leverages both cross-lingual tasks like translation and monolingual tasks like masked language models. Our model achieves an improvement of 2.82 (English to Chinese) and 1.15 (Chinese to English) ROUGE-1 scores over state-of-the-art results.
  arXiv  Detail & Related papers  (2020-10-18T00:21:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.