Meta-Learning Preferences for Multilingual LLM Alignment

• URL: http://arxiv.org/abs/2607.13315v2
• Date: Tue, 21 Jul 2026 18:05:20 GMT
• Title: Meta-Learning Preferences for Multilingual LLM Alignment
• Abstract summary: Unequal availability of human preference data across languages poses a challenge for aligning large language models in multilingual settings.<n>We propose a meta-learning framework for Reinforcement Learning from Human Feedback and Direct Preference Optimization.
• Score: 31.4144889231502
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Unequal availability of human preference data across languages poses a significant challenge for aligning large language models in multilingual settings. To address the lack of sufficient data in low-resource language alignment, we propose a meta-learning framework for Reinforcement Learning from Human Feedback and Direct Preference Optimization. By leveraging preference data from other languages, our framework learns a transferable initialization that enables effective adaptation to a target language with minimal data. We provide theoretical guarantees for both the meta-reward modeling and meta-policy optimization settings, and empirically demonstrate the effectiveness of our approach on multilingual benchmarks. In an extremely low-resource setting with only 100 target-language preference samples, our approach achieves up to $28\%$ win-rate improvements over baseline methods, and consistently outperforms baselines across multiple target languages and model scales. Our approaches retain these advantages across different combinations of meta-training languages and varying linguistic distances from the target languages.

Related papers

• COMPASS: COntinual Multilingual PEFT with Adaptive Semantic Sampling [0.023074632109535153]
  We introduce a data-centric framework for adapting large language models to target languages.<n>We use a distribution-aware sampling strategy to identify semantic gaps between existing training data and a target usage distribution.<n>We extend this into a continual learning framework, which monitors for data distribution shifts in production and dynamically updates adapters to prevent model staleness.
  arXiv  Detail & Related papers  (2026-04-22T16:07:10Z)
• LangGPS: Language Separability Guided Data Pre-Selection for Joint Multilingual Instruction Tuning [49.22807995935406]
  Joint multilingual instruction tuning is a widely adopted approach to improve the multilingual instruction-following ability and downstream performance of large language models (LLMs)<n>Existing selection methods, often based on features like text quality, diversity, or task relevance, typically overlook the intrinsic linguistic structure of multilingual data.<n>We propose LangGPS, a lightweight two-stage pre-selection framework guided by language separability which quantifies how well samples in different languages can be distinguished in the model's representation space.
  arXiv  Detail & Related papers  (2025-11-13T12:02:32Z)
• Exploring Polyglot Harmony: On Multilingual Data Allocation for Large Language Models Pretraining [16.590296049892576]
  This paper introduces Climb, a novel framework designed to systematically optimize multilingual data allocation.<n>At its core, Climb introduces a cross-lingual interaction-aware language ratio, explicitly quantifying each language's effective allocation by capturing inter-language dependencies.<n>Extensive experiments confirm that Climb can accurately measure cross-lingual interactions across various multilingual settings.
  arXiv  Detail & Related papers  (2025-09-19T03:34:34Z)
• 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)
• Enhancing Multilingual LLM Pretraining with Model-Based Data Selection [33.68104398807581]
  We propose a model-based filtering framework for multilingual datasets.<n>Our approach emphasizes transparency, simplicity, and efficiency.<n>We extend our framework to 20 languages for which we release the refined pretraining datasets.
  arXiv  Detail & Related papers  (2025-02-14T18:42:07Z)
• MetaAlign: Align Large Language Models with Diverse Preferences during Inference Time [50.41806216615488]
  Large Language Models (LLMs) acquire extensive knowledge and remarkable abilities from extensive text corpora. To make LLMs more usable, aligning them with human preferences is essential. We propose an effective method, textbf MetaAlign, which aims to help LLMs dynamically align with various explicit or implicit preferences specified at inference time.
  arXiv  Detail & Related papers  (2024-10-18T05:31:13Z)
• Soft Language Clustering for Multilingual Model Pre-training [57.18058739931463]
  We propose XLM-P, which contextually retrieves prompts as flexible guidance for encoding instances conditionally. Our XLM-P enables (1) lightweight modeling of language-invariant and language-specific knowledge across languages, and (2) easy integration with other multilingual pre-training methods.
  arXiv  Detail & Related papers  (2023-06-13T08:08:08Z)
• Distributionally Robust Multilingual Machine Translation [94.51866646879337]
  We propose a new learning objective for Multilingual neural machine translation (MNMT) based on distributionally robust optimization. We show how to practically optimize this objective for large translation corpora using an iterated best response scheme. Our method consistently outperforms strong baseline methods in terms of average and per-language performance under both many-to-one and one-to-many translation settings.
  arXiv  Detail & Related papers  (2021-09-09T03:48:35Z)
• Multilingual and cross-lingual document classification: A meta-learning approach [24.66829920826166]
  We propose a meta-learning approach to document classification in limited-resource setting. We show effectiveness in two settings: few-shot, cross-lingual adaptation to previously unseen languages and multilingual joint training.
  arXiv  Detail & Related papers  (2021-01-27T10:22:56Z)
• Gradient Vaccine: Investigating and Improving Multi-task Optimization in Massively Multilingual Models [63.92643612630657]
  This paper attempts to peek into the black-box of multilingual optimization through the lens of loss function geometry. We find that gradient similarity measured along the optimization trajectory is an important signal, which correlates well with language proximity. We derive a simple and scalable optimization procedure, named Gradient Vaccine, which encourages more geometrically aligned parameter updates for close tasks.
  arXiv  Detail & Related papers  (2020-10-12T17:26:34Z)

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.