paper-with-me

홈 › Papers

Do Multilingual LLMs have specialized language heads?

2026-02-09 · Muhammad Naufil arxiv

Multilingual large language models (LLMs) have gained significant popularity for their ability to process and generate text across multiple languages. However, deploying these models in production can be inefficient when only a subset of the supported languages is of interest. There has been some research conducted on identifying whether machine translation models have language-specific or language-agnostic heads, however no research has been conducted for multilingual LLMs, to the best of our knowledge, that as we know are capable of performing diverse tasks beyond just translation. This paper explores whether multilingual LLMs have specialized language attention heads for each language, and investigates the possibility of removing language-specific heads for unwanted languages without degrading performance in the targeted languages. Our findings could inform more efficient deployment strategies for multilingual LLMs, enabling reduced model complexity while maintaining high accuracy for targeted languages.

📄 PDF Abstract BibTeX arXiv:2602.08625

Code (0)

등록된 구현이 없습니다.

Tasks

Machine Translation

Similar Papers 제목 키워드 기반

Focusing on Language: Revealing and Exploiting Language Attention Heads in Multilingual Large Language Models

2025-11-10 · Xin Liu, Qiyang Song, Qihang Zhou, Haichao Du 외 arxiv

Large language models (LLMs) increasingly support multilingual understanding and generation. Meanwhile, efforts to interpret their internal mechanisms have emerged, offering insights to enhance multilingual performance. …

Exploring Translation Mechanism of Large Language Models

2025-02-17 · Hongbin Zhang, Kehai Chen, Xuefeng Bai, Xiucheng Li 외

Large language models (LLMs) have succeeded remarkably in multilingual translation tasks. However, the inherent translation mechanisms of LLMs remain poorly understood, largely due to sophisticated architectures and vast…

Translation

Bridging Latent Reasoning and Target-Language Generation via Retrieval-Transition Heads

2026-02-25 · Shaswat Patel, Vishvesh Trivedi, Yue Han, Yihuai Hong 외 arxiv

Recent work has identified a subset of attention heads in Transformer as retrieval heads, which are responsible for retrieving information from the context. In this work, we first investigate retrieval heads in multiling…

Soteria: Language-Specific Functional Parameter Steering for Multilingual Safety Alignment

2025-02-16 · Somnath Banerjee, Sayan Layek, Pratyush Chatterjee, Animesh Mukherjee 외

Ensuring consistent safety across multiple languages remains a significant challenge for large language models (LLMs). We introduce Soteria, a lightweight yet powerful strategy that locates and minimally adjusts the "fun…

Safety Alignment

Multilingual Large Language Models: A Systematic Survey

2024-11-17 · Shaolin Zhu, Supryadi, Shaoyang Xu, Haoran Sun 외

This paper provides a comprehensive survey of the latest research on multilingual large language models (MLLMs). MLLMs not only are able to understand and generate language across linguistic boundaries, but also represen…

Cross-Lingual TransferSurvey