paper-with-me

홈 › Papers

MPN: Leveraging Multilingual Patch Neuron for Cross-lingual Model Editing

2024-01-06 · Nianwen Si, Hao Zhang, WeiQiang Zhang

Large language models are known for encoding a vast amount of factual knowledge, but they often becomes outdated due to the ever-changing nature of external information. A promising solution to this challenge is the utilization of model editing methods to update the knowledge in an efficient manner. However, the majority of existing model editing techniques are limited to monolingual frameworks, thus failing to address the crucial issue of cross-lingual knowledge synchronization for multilingual models. To tackle this problem, we propose a simple yet effective method that trains multilingual patch neuron to store cross-lingual knowledge. It can be easily adapted to existing approaches to enhance their cross-lingual editing capabilities. To evaluate our method, we conduct experiments using both the XNLI dataset and a self-constructed XFEVER dataset. Experimental results demonstrate that our proposed method achieves improved performance in cross-lingual editing tasks without requiring excessive modifications to the original methodology, thereby showcasing its user-friendly characteristics. Codes will be released soon.

📄 PDF Abstract BibTeX arXiv:2401.03190

Code (0)

등록된 구현이 없습니다.

Tasks

Model Editing

Similar Papers 제목 키워드 기반

Neuron Specialization: Leveraging intrinsic task modularity for multilingual machine translation

2024-04-17 · Shaomu Tan, Di wu, Christof Monz

Training a unified multilingual model promotes knowledge transfer but inevitably introduces negative interference. Language-specific modeling methods show promise in reducing interference. However, they often rely on heu…

Cross-Lingual TransferMachine TranslationTransfer LearningTranslation

From Neurons to Semantics: Evaluating Cross-Linguistic Alignment Capabilities of Large Language Models via Neurons Alignment

2025-07-20 · Chongxuan Huang, Yongshi Ye, Biao Fu, Qifeng Su 외

Large language models (LLMs) have demonstrated remarkable multilingual capabilities, however, how to evaluate cross-lingual alignment remains underexplored. Existing alignment benchmarks primarily focus on sentence embed…

SentenceSentence Embeddings

Targeted Interpretable Safety Neuron Enhancement for Multilingual Vision-Language Large Models

2026-04-10 · Enyi Shi, Fei Shen, Shuyi Miao, Linxia Zhu 외 arxiv

With the widespread deployment of vision-language large models (VLLMs), their safety alignment faces dual challenges across languages and modalities. Existing methods model multilingual and multimodal safety separately, …

On the Multilingual Ability of Decoder-based Pre-trained Language Models: Finding and Controlling Language-Specific Neurons

2024-04-03 · Takeshi Kojima, Itsuki Okimura, Yusuke Iwasawa, Hitomi Yanaka 외

Current decoder-based pre-trained language models (PLMs) successfully demonstrate multilingual capabilities. However, it is unclear how these models handle multilingualism. We analyze the neuron-level internal behavior o…

DecoderText Generation

Multilingual Knowledge Editing with Language-Agnostic Factual Neurons

2024-06-24 · Xue Zhang, Yunlong Liang, Fandong Meng, Songming Zhang 외

Multilingual knowledge editing (MKE) aims to simultaneously update factual knowledge across multiple languages within large language models (LLMs). Previous research indicates that the same knowledge across different lan…

knowledge editing