解决多语言微调中的冲突，让模型更好区分不同语言。
Multilingual Fine-Tuning via Localized Gradient Conflict Resolution
- 将多语言微调建模为局部梯度优化问题，分桶处理避免通信开销。
- 在4个基座模型上验证，显著提升已见与未见语言的性能。
- 适合需要多语言能力且关注模型泛化性的研究者使用。
大型语言模型（LLMs）的快速发展使其具备跨语言能力，但微调时常引发语言间负向干扰。为此，本文将多语言微调重新定义为多目标优化（MOO）问题，提出可扩展的分布式框架——分桶级多目标优化（Bucket-Level MOO），在参数分桶内局部应用基于梯度的MOO算法，实现冲突感知更新，避免重建完整梯度向量带来的通信开销。理论上，该方法天然满足更严格的精化帕累托稳定条件。实验表明，其通过促使模型构建独立的语言特异性维度，提升表征可分离性，在四个基座模型上的大量实验显示，相比标准微调范式，显著提升了已见与未见语言的表现。
原文摘要 · Abstract (English)
The rapid evolution of Large Language Models (LLMs) has established cross-lingual versatility as a defining feature of modern systems. However, fine-tuning these models frequently induces negative interference across languages. To address this, we reformulate multilingual fine-tuning as a multi-objective optimization (MOO) problem. Specifically, we introduce Bucket-Level MOO, a scalable distributed framework that applies gradient-based MOO algorithms locally on parameter buckets. This enables conflict-aware updates without the prohibitive communication overhead of reconstructing full gradient vectors. Theoretically, we prove this localized resolution natively enforces Refined Pareto Stationarity, a strictly tighter necessary condition for Pareto optimality. Empirically, Bucket-Level MOO mitigates interference by driving LLMs to construct distinct language-specific dimensions, improving representational separability. Extensive experiments across four base LLMs demonstrate that our method significantly improves both seen and unseen multilingual performance over standard fine-tuning paradigms.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。