paper-with-me

홈 › Papers

Multilingual Fine-Tuning via Localized Gradient Conflict Resolution

2026-06-04 · Long P. Hoang, Yiran Zhao, Wei Lu, Wenxuan Zhang arxiv

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.

📄 PDF Abstract BibTeX arXiv:2606.05613

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

CONGRAD:Conflicting Gradient Filtering for Multilingual Preference Alignment

2025-03-31 · Jiangnan Li, Thuy-Trang Vu, Christian Herold, Amirhossein Tebbifakhr 외

Naive joint training of large language models (LLMs) for multilingual preference alignment can suffer from negative interference. This is a known issue in multilingual training, where conflicting objectives degrade overa…

Efficient Model Editing with Task-Localized Sparse Fine-tuning

2025-04-03 · Leonardo Iurada, Marco Ciccone, Tatiana Tommasi

Task arithmetic has emerged as a promising approach for editing models by representing task-specific knowledge as composable task vectors. However, existing methods rely on network linearization to derive task vectors, l…

DisentanglementModel EditingNegationTask Arithmetic

Surgical Knowledge Rewrite in Compact LLMs: An 'Unlearn-then-Learn' Strategy with ($IA^3$) for Localized Factual Modulation and Catastrophic Forgetting Mitigation

2025-08-09 · Stanley Ngugi arxiv

Large Language Models (LLMs) struggle with dynamic knowledge updates, especially when new information conflicts with deeply embedded facts. Such conflicting factual edits often lead to two critical issues: resistance to …

parameter-efficient fine-tuningknowledge editing

Targeting Misalignment: A Conflict-Aware Framework for Reward-Model-based LLM Alignment

2025-12-10 · Zixuan Liu, Siavash H. Khajavi, Guangkai Jiang, Xinru Liu arxiv

Reward-model-based fine-tuning is a central paradigm in aligning Large Language Models with human preferences. However, such approaches critically rely on the assumption that proxy reward models accurately reflect intend…

Gradient Surgery for Safe LLM Fine-Tuning

2025-08-10 · Biao Yi, Jiahao Li, Baolei Zhang, Lihai Nie 외 arxiv

Fine-tuning-as-a-Service introduces a critical vulnerability where a few malicious examples mixed into the user's fine-tuning dataset can compromise the safety alignment of Large Language Models (LLMs). While a recognize…